Decision-Tree, Rule-Based, and Random Forest Classification of High-Resolution Multispectral Imagery for Wetland Mapping and Inventory

Advancements in mapping areas suitable for wetland habitats across the conterminous United States

Wetland habitats provide critical ecosystem services to the surrounding landscape, including nutrient and pollutant retention, flood mitigation, and carbon storage. Wetland connectivity to water bodies and related ecosystems is critical in habitat sustainability, but there are limited resources for landscape-level wetland planning. Considering the network connectivity of an ecosystem type can derive different benefits to the natural and built environment, as well as human health. The value that wetlands provide, along with incentive programs and conservation goals mandated by the government require new and improved wetland spatial data. Utilizing high quality, publicly available data, this study finds that the amount of land in the United States that could support built or restored wetlands is more than double the area of mapped existing wetlands. This study uses 17 input variables (i.e., features extracted from remotely sensed data and auxiliary datasets) at the 10-m resolution and the National Wetlands Inventory to train a random forest model to identify areas that may support a wetland habitat, or potential wetland areas. Models were calculated for each of 18 two-digit hydrologic units that encompass the conterminous United States, and model overall accuracy ranged from 78.0 % to 89.8 %. The models predicted that 21.1 % of the conterminous United States can be categorized as potential wetland area. Selecting input variables to predict areas with wetland potential, rather than to identify existing wetlands, using the random forest algorithm can be transferred to other locations, scales, and ecosystem types. Visualizing potential wetland areas using input data at the 10-m resolution and enhanced methodology improves previous work, as even slight changes in topography, soils, and landscape features can determine ecosystem connections. This product can be used to better place wetland restoration projects to serve ecosystem- and community-wide health by ensuring ecosystem success and targeting areas that face increased climate change impacts.

Multi-Source Remote Sensing Data for Wetland Information Extraction: A Case Study of the Nanweng River National Wetland Reserve

Wetlands play a vital role in regulating the global carbon cycle, providing biodiversity, and reducing flood risks. These functions maintain ecological balance and ensure human well-being. Timely, accurate monitoring of wetlands is essential, not only for conservation efforts, but also for achieving Sustainable Development Goals (SDGs). In this study, we combined Sentinel-1/2 images, terrain data, and field observation data collected in 2020 to better understand wetland distribution. A total of 22 feature variables were extracted from multi-source data, including spectral bands, spectral indices (especially red edge indices), terrain features, and radar features. To avoid high correlations between variables and reduce data redundancy, we selected a subset of features based on recursive feature elimination (RFE) and Pearson correlation analysis methods. We adopted the random forest (RF) method to construct six wetland delineation schemes and incorporated multiple types of characteristic variables. These variables were based on remote sensing image pixels and objects. Combining red-edge features, terrain data, and radar data significantly improved the accuracy of land cover information extracted in low-mountain and hilly areas. Moreover, the accuracy of object-oriented schemes surpassed that of pixel-level methods when applied to wetland classification. Among the three pixel-based schemes, the addition of terrain and radar data increased the overall classification accuracy by 7.26%. In the object-based schemes, the inclusion of radar and terrain data improved classification accuracy by 4.34%. The object-based classification method achieved the best results for swamps, water bodies, and built-up land, with relative accuracies of 96.00%, 90.91%, and 96.67%, respectively. Even higher accuracies were observed in the pixel-based schemes for marshes, forests, and bare land, with relative accuracies of 98.67%, 97.53%, and 80.00%, respectively. This study's methodology can provide valuable reference information for wetland data extraction research and can be applied to a wide range of future research studies.

Precise GDP Spatialization and Analysis in Built-Up Area by Combining the NPP-VIIRS-like Dataset and Sentinel-2 Images

Spatialization and analysis of the gross domestic product of second and tertiary industries (GDP23) can effectively depict the socioeconomic status of regional development. However, existing studies mainly conduct GDP spatialization using nighttime light data; few studies specifically concentrated on the spatialization and analysis of GDP23 in a built-up area by combining multi-source remote sensing images. In this study, the NPP-VIIRS-like dataset and Sentinel-2 multi-spectral remote sensing images in six years were combined to precisely spatialize and analyze the variation patterns of the GDP23 in the built-up area of Zibo city, China. Sentinel-2 images and the random forest (RF) classification method based on PIE-Engine cloud platform were employed to extract built-up areas, in which the NPP-VIIRS-like dataset and comprehensive nighttime light index were used to indicate the nighttime light magnitudes to construct models to spatialize GDP23 and analyze their change patterns during the study period. The results found that (1) the RF classification method can accurately extract the built-up area with an overall accuracy higher than 0.90; the change patterns of built-up areas varied among districts and counties, with Yiyuan county being the only administrative region with an annual expansion rate of more than 1%. (2) The comprehensive nighttime light index is a viable indicator of GDP23 in the built-up area; the fitted model exhibited an R2 value of 0.82, and the overall relative errors of simulated GDP23 and statistical GDP23 were below 1%. (3) The year 2018 marked a significant turning point in the trajectory of GDP23 development in the study area; in 2018, Zhoucun district had the largest decrease in GDP23 at -52.36%. (4) GDP23 gradation results found that Zhangdian district exhibited the highest proportion of high GDP23 (>9%), while the proportions of low GDP23 regions in the remaining seven districts and counties all exceeded 60%. The innovation of this study is that the GDP23 in built-up areas were first precisely spatialized and analyzed using the NPP-VIIRS-like dataset and Sentinel-2 images. The findings of this study can serve as references for formulating improved city planning strategies and sustainable development policies.

How hydrological components of urban blue space influence the thermal milieu?

Present study examines the possible improvement of thermal discomfort mitigation. Unlike prior researches, which focused primarily on cooling effects of urban blue space, this study, instead of physical presence of blue space considers its hydrological components. The aim of the study is to better understand the role hydrological components like water consistency depth etc. In temperature regulation. The work uses field surveys and modeling to demonstrate how these hydrological factors influence the cooling effect of blue space, providing insights on urban thermal management. To fulfill the purpose, spatial association of hydrological components blue space with its thermal environment and cooling effects was assessed. The control of hydrological components on the surrounding air temperature was examined by conducting case studies. RESULTS: reveals greater hydro-duration, deeper water, and higher Water Presence Frequency (WPF) produce greater cooling effects. The study demonstrates a favorable correlation between hydrological richness and temperature reduction. The study also analyzes how land use and wetland size affect temperature, emphasizing the significance of hydrological conservation and restoration for successful temperature mitigation. Due to their hydrology, larger wetlands are able to moderate temperature to some extent, whereas smaller, fragmented wetlands being hydrologically poor are not so influential in this regard. With these results, the present study reaches beyond to the general understanding regarding the cooling effects of the urban blue spaces. While the previous studies primarily focused on estimating the cooling effect of urban blue space, the current one shows its synchronization with the hydrological characteristics. Novelty also entrusts here, through the modeling and field survey current study demonstrates deeper and consistent water coverage in the urban blue space for maximum period of a year pronounces the cooling effect. In addition, in this cooling effect, the role of land use which is a strong determinant of many aspects of the urban environment is also highlighted. Since all these findings define specific hydrological feature, the study has several practical implications. Mare restoration of urban blue space is not enough to mitigate the thermal discomfort. In order to optimize the cooling effect, the conservation of the hydrological richness is essential. The hydrological richness of the smaller wetlands and the edge of the larger wetlands is to be improved. The connection of these wetlands with the adjacent mighty may strengthen the hydrology. The vegetation was found to promote the cooling effect whereas shorter building helped in spreading the cooling effect. Such finding drives to incorporate the blue space with the green infrastructure along with restricting the building height atleast at the edge of the blue space.

Mapping small inland wetlands in the South-Kivu province by integrating optical and SAR data with statistical models for accurate distribution assessment

There are several techniques for mapping wetlands. In this study, we examined four statistical models to assess the potential distribution of wetlands in the South-Kivu province by combining optical and SAR images. The approach involved integrating topographic, hydrological, and vegetation indices into the four most used classifiers, namely Artificial Neural Network (ANN), Random Forest (RF), Boosted Regression Tree (BRT), and Maximum Entropy (MaxEnt). A wetland distribution map was generated and classified into 'wetland' and 'non-wetland.' The results showed variations in predictions among the different models. RF exhibited the most accurate predictions, achieving an overall classification accuracy of 95.67% and AUC and TSS values of 82.4%. Integrating SAR data improved accuracy and precision, particularly for mapping small inland wetlands. Our estimations indicate that wetlands cover approximately 13.5% (898,690 ha) of the entire province. BRT estimated wetland areas to be ~ 16% (1,106,080 ha), while ANN estimated ~ 14% (967,820 ha), MaxEnt ~ 15% (1,036,950 ha), and RF approximately ~ 10% (691,300 ha). The distribution of these areas varied across different territories, with higher values observed in Mwenga, Shabunda, and Fizi. Many of these areas are permanently flooded, while others experience seasonal inundation. Through digitization, the delineation process revealed variations in wetland areas, ranging from tens to thousands of hectares. The geographical distribution of wetlands generated in this study will serve as an essential reference for future investigations and pave the way for further research on characterizing and categorizing these areas.

Paddy Rice mapping in fragmented lands by improved phenology curve and correlation measurements on Sentinel-2 imagery in Google earth engine

Accurate and timely rice crop mapping is important to address the challenges of food security, water management, disease transmission, and land use change. However, accurate rice crop mapping is difficult due to the presence of mixed pixels in small and fragmented rice fields as well as cloud cover. In this paper, a phenology-based method using Sentinel-2 time series images is presented to solve these problems. First, the improved rice phenology curve is extracted based on Normalized Difference Vegetation Index and Land Surface Water Index time series data of rice fields. Then, correlation was taken between rice phenology curve and time series data of each pixel. The correlation result of each pixel shows the similarity of its time series behavior with the proposed rice phenology curve. In the next step, the maximum correlation value and its occurrence time are used as the feature vectors of each pixel to classification. Since correlation measurement provides data with better separability than its input data, training the classifier can be done with fewer samples and the classification is more accurate. The implementation of the proposed correlation-based algorithm can be done in a parallel computing. All the processes were performed on the Google Earth Engine cloud platform on the time series images of the Sentinel 2. The implementations show the high accuracy of this method.

Mapping global non-floodplain wetlands

Non-floodplain wetlands - those located outside the floodplains - have emerged as integral components to watershed resilience, contributing hydrologic and biogeochemical functions affecting watershed-scale flooding extent, drought magnitude, and water-quality maintenance. However, the absence of a global dataset of non-floodplain wetlands limits their necessary incorporation into water quality and quantity management decisions and affects wetland-focused wildlife habitat conservation outcomes. We addressed this critical need by developing a publicly available "Global NFW" (Non-Floodplain Wetland) dataset, comprised of a global river-floodplain map at 90 m resolution coupled with a global ensemble wetland map incorporating multiple wetland-focused data layers. The floodplain, wetland, and non-floodplain wetland spatial data developed here were successfully validated within 21 large and heterogenous basins across the conterminous United States. We identified nearly 33 million potential non-floodplain wetlands with an estimated global extent of over 16×106 km2. Non-floodplain wetland pixels comprised 53% of globally identified wetland pixels, meaning the majority of the globe's wetlands likely occur external to river floodplains and coastal habitats. The identified global NFWs were typically small (median 0.039 km2), with a global median size ranging from 0.018-0.138 km2. This novel geospatial Global NFW static dataset advances wetland conservation and resource-management goals while providing a foundation for global non-floodplain wetland functional assessments, facilitating non-floodplain wetland inclusion in hydrological, biogeochemical, and biological model development. The data are freely available through the United States Environmental Protection Agency's Environmental Dataset Gateway (https://gaftp.epa.gov/EPADataCommons/ORD/Global_NonFloodplain_Wetlands/, last access: 24 May 2023) and through https://doi.org/10.23719/1528331 (Lane et al., 2023a).

Two machine learning approaches for predicting cyanobacteria abundance in aquaculture ponds

Cyanobacteria blooms in aquaculture ponds harm the harvesting of aquatic animals and threaten human health. Therefore, it is crucial to identify key drivers and develop methods to predict cyanobacteria blooms in aquaculture water management. In this study, we analyzed monitoring data from 331 aquaculture ponds in central China and developed two machine learning models - the least absolute shrinkage and selection operator (LASSO) regression model and the random forest (RF) model - to predict cyanobacterial abundance by identifying the key drivers. Simulation results demonstrated that both machine learning models are feasible for predicting cyanobacterial abundance in aquaculture ponds. The LASSO model (R² = 0.918, MSE = 0.354) outperformed the RF model (R² = 0.798, MSE = 0.875) in predicting cyanobacteria abundance. Farmers with well-equipped aquaculture ponds that have abundant water monitoring data can use the nine environmental variables identified by the LASSO model as an operational solution to accurately predict cyanobacteria abundance. For crude ponds with limited monitoring data, the three environmental variables identified by the RF model provide a convenient solution for useful cyanobacteria prediction. Our findings revealed that chemical oxygen demand (COD) and total organic carbon (TOC) were the two most important predictors in both models, indicating that organic carbon concentration had a close relationship with cyanobacteria growth and should be considered a key metric in water monitoring and pond management of these aquaculture ponds. We suggest that monitoring of organic carbon coupled with phosphorus reduction in feed usage can be an effective management approach for cyanobacteria prevention and to maintain a healthy ecological state in aquaculture ponds.

Convolutional neural network for high-resolution wetland mapping with open data: Variable selection and the challenges of a generalizable model

Landscape scale wetland conservation requires accurate, up-to-date wetland maps. The most useful approaches to creating such maps are automated, spatially generalizable, temporally repeatable, and can be applied at large spatial scales. However, mapping wetlands with predictive models is challenging due to the highly variable characteristics of wetlands in both space and time. Currently, most approaches are limited by coarse resolution, commercial data, and geographic specificity. Here, we trained a deep learning model and evaluated its ability to automatically map wetlands at landscape scale in a variety of geographies. We trained a U-Net architecture to map wetlands at 1-meter spatial resolution with the following remotely sensed covariates: multispectral data from the National Agriculture Imagery Program and the Sentinel-2 satellite system, and two LiDAR-derived datasets, intensity and geomorphons. The full model mapped wetlands accurately (94 % accuracy, 96.5 % precision, 95.2 % AUC) at 1-meter resolution. Post hoc model evaluation showed that the model correctly predicted wetlands even in areas that had incorrect label/training data, which penalized the recall rate (90.2 %). Applying the model in a new geography resulted in poor performance (precision = ~80 %, recall = 48 %). However, limited retraining in this geography improved model performance substantially, demonstrating an effective means to create a spatially generalizable model. We demonstrate wetlands can be mapped at high-resolution (1 m) using free data and efficient deep-learning models that do not require manual feature engineering. Including LiDAR and geomorphons as input data improved model accuracy by 2 %, and where these data are unavailable a simpler model can efficiently map wetlands. Given the dynamic nature of wetlands and the important ecosystem services they provide, high-resolution mapping can be a game changer in terms of informing restoration and development decisions.

Predicting In-Hospital Mortality After Acute Myeloid Leukemia Therapy: Through Supervised Machine Learning Algorithms

PURPOSE

Despite careful patient selection, induction chemotherapy for acute myeloid leukemia (AML) is associated with a considerable risk for treatment-related mortality (5%-20%). We evaluated machine learning (ML) algorithms trained using factors available at the time of admission for AML therapy to predict death during the hospitalization.

METHODS

We included AML discharges with age > 17 years who received inpatient chemotherapy from State Inpatient Database from Arizona, Florida, New York, Maryland, Washington, and New Jersey for years 2008-2014. The primary objective was to predict inpatient mortality in patients undergoing chemotherapy using covariates present before initiation of chemotherapy. ML algorithms logistic regression (LR), decision tree, and random forest were compared.

RESULTS

29,613 hospitalizations for patients with AML were included in the analysis each with 4,177 features. The median age was 58.9 (18-101) years, 13,689 (53.7%) were male, and 20,203 (69%) were White. The mean time from admission to chemotherapy was 3 days (95% CI, 2.9 to 3.1), and 2,682 (9.1%) died during the hospitalization. Both LR and random forest models achieved an area under the curve (AUC) score of 0.78, whereas decision tree achieved an AUC of 0.70. The baseline LR model with age yielded an AUC of 0.62. To clinically balance and minimize false positives, we selected a decision threshold of 0.7 and at this threshold, 51 of our test set of 5,923 could have potentially averted treatment-related mortality.

CONCLUSION

Using readily accessible variables, inpatient mortality of patients on track for chemotherapy to treat AML can be predicted through ML algorithms. The model also predicted inpatient mortality when tested on different data representations and paves the way for future research.

Land use change and climate dynamics in the Rift Valley Lake Basin, Ethiopia

Land use and climate dynamics have a pronounced impact on water resources, biodiversity, land degradation, and productivity at all scales. Thus, in this study, we present the spatio-temporal dynamics of land use change and climate aiming to provide a scientific evidence about gains and losses in major land use categories and associated drivers and significancy and homogeneity of climate change. To this end, Landsat images and historical climate data have been used to determine the dynamics. In addition, population census data and land use policy have been considered to assess the potential drivers of land use change. The spatio-temporal land use dynamics have been evaluated using transition matrix and dynamics index. Likewise, shifts in the climate data were analyzed using change point analysis and three homogenous climate zones have been identified using principal component analysis. The results show that, from 1989 to 2019, the areal percentage of agricultural land increased by 27.5%, settlement by 0.8%, and barren land 0.4% while the natural vegetation, wetland, water body, and grass land decreased by 24.5%, 1.6%, 0.5%, and 2.1%, respectively. The land use dynamics have been stronger in the first decade of the study period. An abrupt shift of climate has occurred in the 1980s. In the last four decades, rainfall shows a not significant decreasing trend. However, a significant increasing trend has been observed for temperature. Rapid population growth, agricultural expansion policy, and climate variability have been identified as the underlying drivers of land use dynamics.

A new deep learning approach based on bilateral semantic segmentation models for sustainable estuarine wetland ecosystem management

Nowadays, estuarial areas have been strongly affected by the construction of electrical power dams from upstream, downstream urbanization and many types of hazards along the coastal regions. It has resulted in significant changes in estuarine wetland ecosystems between rainy and dry seasons. To avoid estuary vulnerability, monitoring and evaluation of the estuarine ecosystems are very critical tasks. The main goal of this research is to propose and implement a novel deep learning method in monitoring various ecosystems in estuarine regions. The processing speed and accuracy of common neural networks is improved more than ten times through spatial and context paths integrated into a novel Bilateral Segmentation Network (BiSeNet). The multi-sensor and multi-temporal satellite images (including Sentinel-2, ALOS-DEM, and NOAA-DEM images) served as input data. As a result, four BiSeNet models out of 20 trained models achieved a greater than 90% accuracy, especially for interpreting estuarine waters, intertidal forested wetlands, and aquacultural lands in subtidal regions. These models outperformed Random Forest and Support Vector Machine approaches. The best one was used to map estuarine ecosystems from 12 satellite images over a five-year period in the largest estuary in northern Vietnam. The ecosystem changes between dry and rainy seasons were analyzed in detail to assess the ecological succession in estuaries. Furthermore, this model can potentially update new estuarine ecosystem types in other estuarine areas across the world, making possible real-time monitoring and assessing estuarine ecological conditions for sustainable management of wetland ecosystem.

Assessment of Large-Scale Seasonal River Morphological Changes in Ayeyarwady River Using Optical Remote Sensing Data

Monitoring morphologically dynamic rivers over large spatial domains at an adequate frequency is essential for informed river management to protect human life, ecosystems, livelihoods, and critical infrastructures. Leveraging the advancements in cloud-based remote sensing data processing through Google Earth Engine (GEE), a web-based, freely accessible seasonal river morphological monitoring system for Ayeyarwady River, Myanmar was developed through a collaborative process to assess changes in river morphology over time and space. The monitoring system uses Landsat satellite data spanning a 31-year long period (1988–2019) to map river planform changes along 3881.4 km of river length including Upper Ayeyarwady, Lower Ayeyarwady, and Chindwin. It is designed to operate on a seasonal timescale by comparing pre-monsoon and post-monsoon channel conditions to provide timely information on erosion and accretion areas for the stakeholders to support planning and management. The morphological monitoring system was validated with 85 reference points capturing the field conditions in 2019 and was found to be reliable for operational use with an overall accuracy of 89%. The average eroded riverbank area was calculated at around 45, 101, and 134 km2 for Chindwin, Upper Ayeyarwady, and Lower Ayeyarwady, respectively. The historical channel change assessment aided us to identify and categorize river reaches according to the frequency of changes. Six hotspots of riverbank erosion were identified including near Mandalay city, the confluence of Upper Ayeyarwady and Chindwin, near upstream of Magway city, downstream of Magway city, near Pyay city, and upstream of the Ayeyarwady delta. The web-based monitoring system simplifies the application of freely available remote sensing data over the large spatial domain to assess river planform changes to support stakeholders’ operational planning and prioritizing investments for sustainable Ayeyarwady River management.

Genus-Level Mapping of Invasive Floating Aquatic Vegetation Using Sentinel-2 Satellite Remote Sensing

Invasive floating aquatic vegetation negatively impacts wetland ecosystems and mapping this vegetation through space and time can aid in designing and assessing effective control strategies. Current remote sensing methods for mapping floating aquatic vegetation at the genus level relies on airborne imaging spectroscopy, resulting in temporal gaps because routine hyperspectral satellite coverage is not yet available. Here we achieved genus level and species level discrimination between two invasive aquatic vegetation species using Sentinel 2 multispectral satellite data and machine-learning classifiers in summer and fall. The species of concern were water hyacinth (Eichornia crassipes) and water primrose (Ludwigia spp.). Our classifiers also identified submerged and emergent aquatic vegetation at the community level. Random forest models using Sentinel-2 data achieved an average overall accuracy of 90%, and class accuracies of 79–91% and 85–95% for water hyacinth and water primrose, respectively. To our knowledge, this is the first study that has mapped water primrose to the genus level using satellite remote sensing. Sentinel-2 derived maps compared well to those derived from airborne imaging spectroscopy and we also identified misclassifications that can be attributed to the coarser Sentinel-2 spectral and spatial resolutions. Our results demonstrate that the intra-annual temporal gaps between airborne imaging spectroscopy observations can be supplemented with Sentinel-2 satellite data and thus, rapidly growing/expanding vegetation can be tracked in real time. Such improvements have potential management benefits by improving the understanding of the phenology, spread, competitive advantages, and vulnerabilities of these aquatic plants.

Identification and Counting of European Souslik Burrows from UAV Images by Pixel-Based Image Analysis and Random Forest Classification: A Simple, Semi-Automated, yet Accurate Method for Estimating Population Size

Burrowing mammals such as European sousliks are widespread and contribute significantly to soil ecosystem services. However, they have declined across their range and the non-invasive estimation of their actual population size has remained a challenge. Results support that the number of burrow entrances is positively correlated with population abundance, and burrow locations indicate the occupied area. We present an imagery-based method to identify and count animals’ burrows semi-automatically by combining remotely recorded red, green, and blue (RGB) images, pixel-based imagery, and random forest (RF) classification. Field images were collected for four colonies, then combined and processed by histogram matching and spectral band normalization to improve the spectral distinctions among the categories BURROW, SOIL, TREE, and GRASS. The accuracy indexes of classification for BURROW kappa (κ) were 95% (precision) and 90% (sensitivity). A 10-iteration bootstrapping of the final model resulted in coefficients of variation (CV%) of BURROW κ for sensitivity and precision lower than 5%; moreover, CV% values were not significantly different between those scores. The consistency of classification and balanced precision and sensitivity confirmed the applicability of this approach. Our approach provides an accurate, user-friendly, and relatively simple approach to count the number of burrow openings, estimate population abundance, and delineate the areas of occupancy non-invasively.

Automatic Air-to-Ground Recognition of Outdoor Injured Human Targets Based on UAV Bimodal Information: The Explore Study

The rapid air-to-ground search of injured people in the outdoor environment has been a hot spot and a great challenge for public safety and emergency rescue medicine. Its crucial difficulties lie in the fact that small-scale human targets possess a low target-background contrast to the complex outdoor environment background and the human attribute of the target is hard to verify. Therefore, an automatic recognition method based on UAV bimodal information is proposed in this paper. First, suspected targets were accurately detected and separated from the background based on multispectral feature information only. Immediately after, the bio-radar module would be released and would try to detect their corresponding physiological information for accurate re-identification of the human target property. Both the suspected human target detection experiments and human target property re-identification experiments show that our proposed method could effectively realize accurate identification of ground injured in outdoor environments, which is meaningful for the research of rapid search and rescue of injured people in the outdoor environment.

Performance comparison of deep learning and machine learning methods in determining wetland water areas using EuroSAT dataset

Wetlands are critical to the ecology because they maintain biodiversity and provide home for a variety of species. Researching, mapping, and conservation of wetlands is a challenging and time-consuming process. Because they produce temporal and geographical information, remote sensing and photogrammetric approaches are useful tools for analyzing and managing wetlands. In this study, the water areas of five different wetlands obtained with Sentinel-2 images in Turkey were classified. Although obtaining large amounts of high-dimensional dataset labeled for various land types is costly, it is a significant advantage to use it after model training in a wide range of applications. In this paper, the EuroSAT dataset was used in the validation process. Proposed deep learning-based 1D convolutional neural networks (CNN) and traditional machine learning methods (i.e., support vector machine, linear discriminant analysis, K-nearest neighborhood, canonical correlation forests, and AdaBoost.M1) were compared quantitatively (i.e., accuracy, recall, precision, specificity, F-score, and image quality assessment metrics) and qualitatively. Finally, pairwise comparison was made with chi-square-based McNemar's test. There is a statistical difference between 1D CNN and machine learning method (except the support vector machine vs linear discriminant analysis in Test 1 area). CNN models outperform machine learning algorithms in terms of non-linear function approximation and the ability to extract and articulate data features. Since 1D CNNs can process data in a highly complex and unique feature space, they are very successful in segmenting strongly related and highly correlated discrete signals. It also has advantages over machine learning methods for water body extraction in that it can be integrated with sophisticated image pre-processing and standardization tools, is less susceptible to low-level random noise, and provides shift in variations and contrast-invariant image local transforms.

A Deep Learning Approach to Analyze Airline Customer Propensities: The Case of South Korea

In the airline industry, customer satisfaction occurs when passengers’ expectations are met through the airline experience. Considering that airline service quality is the main factor in obtaining new and retaining existing customers, airline companies are applying various approaches to improve the quality of the physical and social servicescapes. It is common to use data analysis techniques for analyzing customer propensity in marketing. However, their application to the airline industry has traditionally focused solely on surveys; hence, there is a lack of attention paid to deep learning techniques based on survey results. This study has two purposes. The first purpose is to find the relationship between various factors influencing customer churn risk and satisfaction by analyzing the airline customer data. For this, we applied deep learning techniques to the survey data collected from the users who have used mostly Korean airplanes. To the best of our knowledge, this is the one of the few attempts at applying deep learning to analyze airline customer propensities. The second purpose is to analyze the influence of the social servicescape, including the viewpoints of the cabin crew and passengers using aircraft, on airline customer propensities. The experimental results demonstrated that the proposed method of considering human services increased the accuracy of predictive models by up to 10% and 9% in predicting customer churn risk and satisfaction, respectively.

A Machine Learning Framework for the Classification of Natura 2000 Habitat Types at Large Spatial Scales Using MODIS Surface Reflectance Data

Anthropogenic climate and land use change is causing rapid shifts in the distribution and composition of habitats with profound impacts on ecosystem biodiversity. The sustainable management of ecosystems requires monitoring programmes capable of detecting shifts in habitat distribution and composition at large spatial scales. Remote sensing observations facilitate such efforts as they enable cost-efficient modelling approaches that utilize publicly available datasets and can assess the status of habitats over extended periods of time. In this study, we introduce a modelling framework for habitat monitoring in Germany using readily available MODIS surface reflectance data. We developed supervised classification models that allocate (semi-)natural areas to one of 18 classes based on their similarity to Natura 2000 habitat types. Three machine learning classifiers, i.e., Support Vector Machines (SVM), Random Forests (RF), and C5.0, and an ensemble approach were employed to predict habitat type using spectral signatures from MODIS in the visible-to-near-infrared and short-wave infrared. The models were trained on homogenous Special Areas of Conservation that are predominantly covered by a single habitat type with reference data from 2013, 2014, and 2016 and tested against ground truth data from 2010 and 2019 for independent model validation. Individually, the SVM and RF methods achieved better overall classification accuracies (SVM: 0.72–0.93%, RF: 0.72–0.94%) than the C5.0 algorithm (0.66–0.93%), while the ensemble classifier developed from the individual models gave the best performance with overall accuracies of 94.23% for 2010 and 80.34% for 2019 and also allowed a robust detection of non-classifiable pixels. We detected strong variability in the cover of individual habitat types, which were reduced when aggregated based on their similarity. Our methodology is capable to provide quantitative information on the spatial distribution of habitats, differentiate between disturbance events and gradual shifts in ecosystem composition, and could successfully allocate natural areas to Natura 2000 habitat types.

Land Cover Changes in Selected Areas Next to Lagoons Located on the Southern Coast of the Baltic Sea, 1984–2021

The aim of the study is the evaluation of land cover changes in selected areas next to three lagoons (the Curonian Lagoon, the Vistula Lagoon and the Szczecin Lagoon) located on the southern coast of the Baltic Sea (in Lithuania, Russia, Poland and Germany) from 1984 to 2021. The changes are evaluated using multispectral (visible light—RGB and near infrared—NIR) satellite images from the Landsat 5 and Sentinel-2 sensors. Due to their high importance for ecosystem services, two main land cover types are evaluated, i.e., forest area and inland water reservoirs. The classification of the images is performed using a random forest algorithm. Areas of water bodies and forests are evaluated for the years 1984 and 2021. During period 1984–2021, positive changes in land cover are observed in all three regions included in the study. In almost all parts, with the exception of the Polish part of the area located next to the Szczecin Lagoon, of these regions, an increase in forest area is observed. The increase ranges from 0.1% (Poland, area next to the Vistula Lagoon) to 1.2% (Germany, area next to the Szczecin Lagoon). The area of inland water reservoirs has not changed significantly in the long term. Despite the global warming, no reduction in the area of these water reservoirs is observed, even new seminatural reservoirs have been created in some parts of the study area.

Cotton Classification Method at the County Scale Based on Multi-Features and Random Forest Feature Selection Algorithm and Classifier

Accurate cotton maps are crucial for monitoring cotton growth and precision management. The paper proposed a county-scale cotton mapping method by using random forest (RF) feature selection algorithm and classifier based on selecting multi-features, including spectral, vegetation indices, and texture features. The contribution of texture features to cotton classification accuracy was also explored in addition to spectral features and vegetation index. In addition, the optimal classification time, feature importance, and the best classifier on the cotton extraction accuracy were evaluated. The results showed that the texture feature named the gray level co-occurrence matrix (GLCM) is effective for improving classification accuracy, ranking second in contribution among all studied spectral, VI, and texture features. Among the three classifiers, the RF showed higher accuracy and better stability than support vector machines (SVM) and artificial neural networks (ANN). The average overall accuracy (OA) of the classification combining multiple features was 93.36%, 7.33% higher than the average OA of the single-time spectrum, and 2.05% higher than the average OA of the multi-time spectrum. The classification accuracy after feature selection by RF can still reach 92.12%, showing high accuracy and efficiency. Combining multiple features and random forest methods may be a promising county-scale cotton classification method.

Fine-Scale Mapping of Natural Ecological Communities Using Machine Learning Approaches

Remote sensing technology has been used widely in mapping forest and wetland communities, primarily with moderate spatial resolution imagery and traditional classification techniques. The success of these mapping efforts varies widely. The natural communities of the Laurentian Mixed Forest are an important component of Upper Great Lakes ecosystems. Mapping and monitoring these communities using high spatial resolution imagery benefits resource management, conservation and restoration efforts. This study developed a robust classification approach to delineate natural habitat communities utilizing multispectral high-resolution (60 cm) National Agriculture Imagery Program (NAIP) imagery data. For accurate training set delineation, NAIP imagery, soils data and spectral enhancement techniques such as principal component analysis (PCA) and independent component analysis (ICA) were integrated. The study evaluated the importance of biogeophysical parameters such as topography, soil characteristics and gray level co-occurrence matrix (GLCM) textures, together with the normalized difference vegetation index (NDVI) and NAIP water index (WINAIP) spectral indices, using the joint mutual information maximization (JMIM) feature selection method and various machine learning algorithms (MLAs) to accurately map the natural habitat communities. Individual habitat community classification user’s accuracies (UA) ranged from 60 to 100%. An overall accuracy (OA) of 79.45% (kappa coefficient (k): 0.75) with random forest (RF) and an OA of 75.85% (k: 0.70) with support vector machine (SVM) were achieved. The analysis showed that the use of the biogeophysical ancillary data layers was critical to improve interclass separation and classification accuracy. Utilizing widely available free high-resolution NAIP imagery coupled with an integrated classification approach using MLAs, fine-scale natural habitat communities were successfully delineated in a spatially and spectrally complex Laurentian Mixed Forest environment.

Swin Transformer for Complex Coastal Wetland Classification Using the Integration of Sentinel-1 and Sentinel-2 Imagery

The emergence of deep learning techniques has revolutionized the use of machine learning algorithms to classify complicated environments, notably in remote sensing. Convolutional Neural Networks (CNNs) have shown considerable promise in classifying challenging high-dimensional remote sensing data, particularly in the classification of wetlands. State-of-the-art Natural Language Processing (NLP) algorithms, on the other hand, are transformers. Despite the fact that transformers have been utilized for a few remote sensing applications, they have not been compared to other well-known CNN networks in complex wetland classification. As such, for the classification of complex coastal wetlands in the study area of Saint John city, located in New Brunswick, Canada, we modified and employed the Swin Transformer algorithm. Moreover, the developed transformer classifier results were compared with two well-known deep CNNs of AlexNet and VGG-16. In terms of average accuracy, the proposed Swin Transformer algorithm outperformed the AlexNet and VGG-16 techniques by 14.3% and 44.28%, respectively. The proposed Swin Transformer classifier obtained F-1 scores of 0.65, 0.71, 0.73, 0.78, 0.82, 0.84, and 0.84 for the recognition of coastal marsh, shrub, bog, fen, aquatic bed, forested wetland, and freshwater marsh, respectively. The results achieved in this study suggest the high capability of transformers over very deep CNN networks for the classification of complex landscapes in remote sensing.

Aquatic Vegetation Loss and Its Implication on Climate Regulation in a Protected Freshwater Wetland of Po River Delta Park (Italy)

Aquatic vegetation loss caused substantial decrease of ecosystem processes and services during the last decades, particularly for the capacity of these ecosystems to sequester and store carbon from the atmosphere. This study investigated the extent of aquatic emergent vegetation loss for the period 1985–2018 and the consequent effects on carbon sequestration and storage capacity of Valle Santa wetland, a protected freshwater wetland dominated by Phragmites australis located in the Po river delta Park (Northern Italy), as a function of primary productivity and biomass decomposition, assessed by means of satellite images and experimental measures. The results showed an extended loss of aquatic vegetated habitats during the considered period, with 1989 being the year with higher productivity. The mean breakdown rates of P. australis were 0.00532 d−1 and 0.00228 d−1 for leaf and stem carbon content, respectively, leading to a predicted annual decomposition of 64.6% of the total biomass carbon. For 2018 the carbon sequestration capacity was estimated equal to 0.249 kg C m−2 yr−1, while the carbon storage of the whole wetland was 1.75 × 103 t C (0.70 kg C m−2). Nonetheless, despite the protection efforts over time, the vegetation loss occurred during the last decades significantly decreased carbon sequestration and storage by 51.6%, when comparing 2018 and 1989. No statistically significant effects were found for water descriptors. This study demonstrated that P. australis-dominated wetlands support important ecosystem processes and should be regarded as an important carbon sink under an ecosystem services perspective, with the aim to maximize their capacity to mitigate climate change.

Informing Equitable Water and Food Policies through Accurate Spatial Information on Irrigated Areas in Smallholder Farming Systems

Accurate information on irrigated areas' spatial distribution and extent are crucial in enhancing agricultural water productivity, water resources management, and formulating strategic policies that enhance water and food security and ecologically sustainable development. However, data are typically limited for smallholder irrigated areas, which is key to achieving social equity and equal distribution of financial resources. This study addressed this gap by delineating disaggregated smallholder and commercial irrigated areas through the random forest algorithm, a non-parametric machine learning classifier. Location within or outside former apartheid "homelands" was taken as a proxy for smallholder, and commercial irrigation. Being in a medium rainfall area, the huge irrigation potential of the Inkomati-Usuthu Water Management Area (UWMA) is already well developed for commercial crop production outside former homelands. However, information about the spatial distribution and extent of irrigated areas within former homelands, which is largely informal, was missing. Therefore, we first classified cultivated lands in 2019 and 2020 as a baseline, from where the Normalised Difference Vegetation Index (NDVI) was used to distinguish irrigated from rainfed, focusing on the dry winter period when crops are predominately irrigated. The mapping accuracy of 84.9% improved the efficacy in defining the actual spatial extent of current irrigated areas at both smallholder and commercial spatial scales. The proportion of irrigated areas was high for both commercial (92.5%) and smallholder (96.2%) irrigation. Moreover, smallholder irrigation increased by over 19% between 2019 and 2020, compared to slightly over 7% in the commercial sector. Such information is critical for policy formulation regarding equitable and inclusive water allocation, irrigation expansion, land reform, and food and water security in smallholder farming systems.

A Synergic Use of Sentinel-1 and Sentinel-2 Imagery for Complex Wetland Classification Using Generative Adversarial Network (GAN) Scheme

Due to anthropogenic activities and climate change, many natural ecosystems, especially wetlands, are lost or changing at a rapid pace. For the last decade, there has been increasing attention towards developing new tools and methods for the mapping and classification of wetlands using remote sensing. At the same time, advances in artificial intelligence and machine learning, particularly deep learning models, have provided opportunities to advance wetland classification methods. However, the developed deep and very deep algorithms require a higher number of training samples, which is costly, logistically demanding, and time-consuming. As such, in this study, we propose a Deep Convolutional Neural Network (DCNN) that uses a modified architecture of the well-known DCNN of the AlexNet and a Generative Adversarial Network (GAN) for the generation and classification of Sentinel-1 and Sentinel-2 data. Applying to an area of approximately 370 sq. km in the Avalon Peninsula, Newfoundland, the proposed model with an average accuracy of 92.30% resulted in F-1 scores of 0.82, 0.85, 0.87, 0.89, and 0.95 for the recognition of swamp, fen, marsh, bog, and shallow water, respectively. Moreover, the proposed DCNN model improved the F-1 score of bog, marsh, fen, and swamp wetland classes by 4%, 8%, 11%, and 26%, respectively, compared to the original CNN network of AlexNet. These results reveal that the proposed model is highly capable of the generation and classification of Sentinel-1 and Sentinel-2 wetland samples and can be used for large-extent classification problems.

Retrieving dynamics of the surface water extent in the upper reach of Yellow River

Multi-time scale surface water extent (SWE) dynamics are very important to understand climate change impacts on water resources. With Landsat 5/7/8 images and Google Earth Engine (GEE), an improved threshold-based water extraction algorithm and a novel surface water gaps (SWGs) interpolation method based on historical water frequency were applied to build surface water area (SWA, namely SWE without ice) and water body area (WBA, namely SWE with ice) monthly (January 2001-December 2019) and annual (1986-2019) time series in the upper reaches of the Yellow River (UYR). The Mann-Kendall test was used to analyse SWE trends, and the ridge regression was performed to figure out the relative contributions of meteorological factors to SWE dynamics. The pixels with modified normalized difference water index (MNDWI) higher than normalized difference vegetation index (NDVI) or enhanced vegetation index (EVI) were identified as SWE. The mean relative error (MRE) of the SWGs interpolation results was below 10%. At the annual scale, the average SWA and number of lakes over 1 ha showed significant upward trends of 4.4 km² yr^-1 and 7.53 yr^-1, respectively. The monthly WBA increased in summer and autumn while decreased in spring and winter. The maximum freezing and thawing ratios were 53.74% in December and 37.32% in May, respectively. Attribution analysis showed that precipitation and wind speed were the foremost factors dominating the dynamics of annual SWA and monthly WBA, respectively. Our findings confirmed that climatic changes have altered the dynamics of water bodies in the UYR.

Drivers and extent of surface water occurrence in the Selenga River Delta, Russia

STUDY REGION

Selenga River Delta (SRD), Russia.

STUDY FOCUS

How is water occurrence changing in the SRD, and what are the hydroclimatic drivers behind these changes? The presence of water on the surface in river deltas is governed by land use, geomorphology, and the flux of water to and from the Delta. We trained an accurate image classification of the Landsat satellite imagery during the last 33 years to quantify surface water occurrence and its changes in the SRD. After comparing our estimations with global-scale datasets, we determined the hydrological drivers of these changes.

NEW HYDROLOGICAL INSIGHTS FOR THE REGION

We find mild decreases in water occurrence in 51% of the SRD's surface area from 1987-2002 to 2003-2020. Water occurrence in the most affected areas decreased by 20% and in the most water-gaining areas increased by 10%. We find a significant relationship between water occurrence and runoff (R² = 0.56) that does not exist between water occurrence and suspended sediment concentration (SSC), Lake Baikal's water level, and potential evapotranspiration. The time series of water occurrence follows the peaks in the runoff but not its long-term trend. However, the extremes in SSC do not influence surface water occurrence (R² < 0.1), although their long-term trends are similar. Contrary to expected, we find that the Delta has a relatively stable long-term water availability for the time being.

A Training Sample Migration Method for Wetland Mapping and Monitoring Using Sentinel Data in Google Earth Engine

Wetlands are one of the most important ecosystems due to their critical services to both humans and the environment. Therefore, wetland mapping and monitoring are essential for their conservation. In this regard, remote sensing offers efficient solutions due to the availability of cost-efficient archived images over different spatial scales. However, a lack of sufficient consistent training samples at different times is a significant limitation of multi-temporal wetland monitoring. In this study, a new training sample migration method was developed to identify unchanged training samples to be used in wetland classification and change analyses over the International Shadegan Wetland (ISW) areas of southwestern Iran. To this end, we first produced the wetland map of a reference year (2020), for which we had training samples, by combining Sentinel-1 and Sentinel-2 images and the Random Forest (RF) classifier in Google Earth Engine (GEE). The Overall Accuracy (OA) and Kappa coefficient (KC) of this reference map were 97.93% and 0.97, respectively. Then, an automatic change detection method was developed to migrate unchanged training samples from the reference year to the target years of 2018, 2019, and 2021. Within the proposed method, three indices of the Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), and the mean Standard Deviation (SD) of the spectral bands, along with two similarity measures of the Euclidean Distance (ED) and Spectral Angle Distance (SAD), were computed for each pair of reference–target years. The optimum threshold for unchanged samples was also derived using a histogram thresholding approach, which led to selecting the samples that were most likely unchanged based on the highest OA and KC for classifying the test dataset. The proposed migration sample method resulted in high OAs of 95.89%, 96.83%, and 97.06% and KCs of 0.95, 0.96, and 0.96 for the target years of 2018, 2019, and 2021, respectively. Finally, the migrated samples were used to generate the wetland map for the target years. Overall, our proposed method showed high potential for wetland mapping and monitoring when no training samples existed for a target year.

Mangrove Forest Cover and Phenology with Landsat Dense Time Series in Central Queensland, Australia

Wetlands are one of the most biologically productive ecosystems. Wetland ecosystem services, ranging from provision of food security to climate change mitigation, are enormous, far outweighing those of dryland ecosystems per hectare. However, land use change and water regulation infrastructure have reduced connectivity in many river systems and with floodplain and estuarine wetlands. Mangrove forests are critical communities for carbon uptake and storage, pollution control and detoxification, and regulation of natural hazards. Although the clearing of mangroves in Australia is strictly regulated, Great Barrier Reef catchments have suffered landscape modifications and hydrological alterations that can kill mangroves. We used remote sensing datasets to investigate land cover change and both intra- and inter-annual seasonality in mangrove forests in a large estuarine region of Central Queensland, Australia, which encompasses a national park and Ramsar Wetland, and is adjacent to the Great Barrier Reef World Heritage site. We built a time series using spectral, auxiliary, and phenology variables with Landsat surface reflectance products, accessed in Google Earth Engine. Two land cover classes were generated (mangrove versus non-mangrove) in a Random Forest classification. Mangroves decreased by 1480 hectares (−2.31%) from 2009 to 2019. The overall classification accuracies and Kappa coefficient for 2008–2010 and 2018–2020 land cover maps were 95% and 95%, respectively. Using an NDVI-based time series we examined intra- and inter-annual seasonality with linear and harmonic regression models, and second with TIMESAT metrics of mangrove forests in three sections of our study region. Our findings suggest a relationship between mangrove growth phenology along with precipitation anomalies and severe tropical cyclone occurrence over the time series. The detection of responses to extreme events is important to improve understanding of the connections between climate, extreme weather events, and biodiversity in estuarine and mangrove ecosystems.

Mapping Alkaline Fens, Transition Mires and Quaking Bogs Using Airborne Hyperspectral and Laser Scanning Data

The aim of this study is to evaluate the effectiveness of the identification of Natura 2000 wetland habitats (Alkaline fens—code 7230, and Transition mires and quaking bogs—code 7140) depending on various remotely sensed (RS) data acquired from an airborne platform. Both remote sensing data and botanical reference data were gathered for mentioned habitats in the Lower (LB) and Upper Biebrza (UB) River Valley and the Janowskie Forest (JF) in different seasonal stages. Several different classification scenarios were tested, and the ones that gave the best results for analyzed habitats were indicated in each campaign. In the final stage, a recommended term of data acquisition, as well as a list of remote sensing products, which allowed us to achieve the highest accuracy mapping for these two types of wetland habitats, were presented. Designed classification scenarios integrated different hyperspectral products such as Minimum Noise Fraction (MNF) bands, spectral indices and products derived from Airborne Laser Scanning (ALS) data representing topography (developed in SAGA), or statistical products (developed in OPALS—Orientation and Processing of Airborne Laser Scanning). The image classifications were performed using a Random Forest (RF) algorithm and a multi-classification approach. As part of the research, the correlation analysis of the developed remote sensing products was carried out, and the Recursive Feature Elimination with Cross-Validation (RFE-CV) analysis was performed to select the most important RS sub-products and thus increase the efficiency and accuracy of developing the final habitat distribution maps. The classification results showed that alkaline fens are better identified in summer (mean F1-SCORE equals 0.950 in the UB area, and 0.935 in the LB area), transition mires and quaking bogs that evolved on/or in the vicinity of alkaline fens in summer and autumn (mean F1-SCORE equals 0.931 in summer, and 0.923 in autumn in the UB area), and transition mires and quaking bogs that evolved on dystrophic lakes in spring and summer (mean F1-SCORE equals 0.953 in spring, and 0.948 in summer in the JF area). The study also points out that the classification accuracy of both wetland habitats is highly improved when combining selected hyperspectral products (MNF bands, spectral indices) with ALS topographical and statistical products. This article demonstrates that information provided by the synergetic use of data from different sensors can be used in mapping and monitoring both Natura 2000 wetland habitats for its future functional assessment and/or protection activities planning with high accuracy.

A classifier-combined method based on D-S evidence theory for the land cover classification of the Tibetan Plateau

The Tibetan Plateau (TP) is a region with high altitudes and complicated terrain conditions. Due to the special conditions of this region, it is also regarded as the third pole of the Earth. The land cover and vegetation in this region have not been extensively studied, so this study investigated the possibility of using a combined classifier that was established based on D-S evidence theory to extract the land cover of the TP. Multiple feature images were obtained based on a single classification rule, and the feature images were normalized to obtain the basic probability assignment (BPA). The BPA was used as the evidence source to represent the belief level of each type of land cover. The information for the different belief levels was combined based on the D-S evidence theory. The maximum belief level of the combination results was used to identify the land cover types on the TP. The results of this study indicate that based on the D-S evidence theory, multiple classifiers can effectively be combined to improve the classification results. This study has also revealed that more classifiers fused together to make a combined classifier did not result in the combined classifier's accuracy being higher than those of the original classifiers. Higher accuracies were only obtained when more high accuracy evidence theory was used in the classifier combination, in which case, the combined classifier's classification accuracy was also high.

Application of the Random Forest Classifier to Map Irrigated Areas Using Google Earth Engine

Improvements in irrigated areas' classification accuracy are critical to enhance agricultural water management and inform policy and decision-making on irrigation expansion and land use planning. This is particularly relevant in water-scarce regions where there are plans to increase the land under irrigation to enhance food security, yet the actual spatial extent of current irrigation areas is unknown. This study applied a non-parametric machine learning algorithm, the random forest, to process and classify irrigated areas using images acquired by the Landsat and Sentinel satellites, for Mpumalanga Province in Africa. The classification process was automated on a big-data management platform, the Google Earth Engine (GEE), and the R-programming was used for post-processing. The normalised difference vegetation index (NDVI) was subsequently used to distinguish between irrigated and rainfed areas during 2018/19 and 2019/20 winter growing seasons. High NDVI values on cultivated land during the dry season are an indication of irrigation. The classification of cultivated areas was for 2020, but 2019 irrigated areas were also classified to assess the impact of the Covid-19 pandemic on agriculture. The comparison in irrigated areas between 2019 and 2020 facilitated an assessment of changes in irrigated areas in smallholder farming areas. The approach enhanced the classification accuracy of irrigated areas using ground-based training samples and very high-resolution images (VHRI) and fusion with existing datasets and the use of expert and local knowledge of the study area. The overall classification accuracy was 88%.

Antiplasmodial activity of sulfonylhydrazones: in vitro and in silico approaches

Malaria is still a life-threatening public health issue, and the upsurge of resistant strains requires continuous generation of active molecules. In this work, 35 sulfonylhydrazone derivatives were synthesized and evaluated against Plasmodium falciparum chloroquine-sensitive (3D7) and resistant (W2) strains. The most promising compound, 5b, had an IC₅₀ of 0.22 μM against W2 and was less cytotoxic and 26-fold more selective than chloroquine. The structure-activity relationship model, statistical analysis and molecular modeling studies suggested that antiplasmodial activity was related to hydrogen bond acceptor count, molecular weight and partition coefficient of octanol/water and displacement of frontier orbitals to the heteroaromatic ring beside the imine bond. This study demonstrates that the synthesized molecules with a simple scaffold allow the hit-to-lead process for new antimalarials to commence.

Improved Prototypical Network Model for Forest Species Classification in Complex Stand

Deep learning has become an effective method for hyperspectral image classification. However, the high band correlation and data volume associated with airborne hyperspectral images, and the insufficiency of training samples, present challenges to the application of deep learning in airborne image classification. Prototypical networks are practical deep learning networks that have demonstrated effectiveness in handling small-sample classification. In this study, an improved prototypical network is proposed (by adding L2 regularization to the convolutional layer and dropout to the maximum pooling layer) to address the problem of overfitting in small-sample classification. The proposed network has an optimal sample window for classification, and the window size is related to the area and distribution of the study area. After performing dimensionality reduction using principal component analysis, the time required for training using hyperspectral images shortened significantly, and the test accuracy increased drastically. Furthermore, when the size of the sample window was 27 × 27 after dimensionality reduction, the overall accuracy of forest species classification was 98.53%, and the Kappa coefficient was 0.9838. Therefore, by using an improved prototypical network with a sample window of an appropriate size, the network yielded desirable classification results, thereby demonstrating its suitability for the fine classification and mapping of tree species.

Land use and land cover changes along the China-Myanmar Oil and Gas pipelines - Monitoring infrastructure development in remote conflict-prone regions

Energy infrastructures can have negative impacts on the environment. In remote and / or sparsely populated as well as in conflict-prone regions, these can be difficult to assess, in particular when they are of a large scale. Analyzing land use and land cover changes can be an important initial step towards establishing the quantity and quality of impacts. Drawing from very-high-resolution-multi-temporal-satellite-imagery, this paper reports on a study which employed the Random Forest Classifier and Land Change Modeler to derive detailed information of the spatial patterns and temporal variations of land-use and land-cover changes resulting from the China-Myanmar Oil and Gas Pipelines in Ann township in Myanmar’s Rakhine State of Myanmar. Deforestation and afforestation conversion processes during pre- and post-construction periods (2010 to 2012) are compared. Whilst substantial forest areas were lost along the pipelines, this is only part of the story, as afforestation has also happened in parallel. However, afforestation areas can be of a lower value, and in order to be able to take quality of forests into account, it is of crucial importance to accompany satellite-imagery based techniques with field observation. Findings have important implications for future infrastructure development projects in conflict-affected regions in Myanmar and elsewhere.

Synergy of High-Resolution Radar and Optical Images Satellite for Identification and Mapping of Wetland Macrophytes on the Danube Delta

In wetland environments, vegetation has an important role in ecological functioning. The main goal of this work was to identify an optimal combination of Sentinel-1 (S1), Sentinel-2 (S2), and Pleiades data using ground-reference data to accurately map wetland macrophytes in the Danube Delta. We tested several combinations of optical and Synthetic Aperture Radar (SAR) data rigorously at two levels. First, in order to reduce the confusion between reed (Phragmites australis (Cav.) Trin. ex Steud.) and other macrophyte communities, a time series analysis of S1 data was performed. The potential of S1 for detection of compact reed on plaur, compact reed on plaur/reed cut, open reed on plaur, pure reed, and reed on salinized soil was evaluated through time series of backscatter coefficient and coherence ratio images, calculated mainly according to the phenology of the reed. The analysis of backscattering coefficients allowed separation of reed classes that strongly overlapped. The coherence coefficient showed that C-band SAR repeat pass interferometric coherence for cut reed detection is feasible. In the second section, random forest (RF) classification was applied to the S2, Pleiades, and S1 data and in situ observations to discriminate and map reed against other aquatic macrophytes (submerged aquatic vegetation (SAV), emergent macrophytes, some floating broad-leaved and floating vegetation of delta lakes). In addition, different optical indices were included in the RF. A total of 67 classification models were made in several sensor combinations with two series of validation samples (with the reed and without reed) using both a simple and more detailed classification schema. The results showed that reed is completely discriminable compared to other macrophyte communities with all sensor combinations. In all combinations, the model-based producer’s accuracy (PA) and user’s accuracy (UA) for reed with both nomenclatures were over 90%. The diverse combinations of sensors were valuable for improving the overall classification accuracy of all of the communities of aquatic macrophytes except Myriophyllum spicatum L.

Coastal Wetland Mapping Using Ensemble Learning Algorithms: A Comparative Study of Bagging, Boosting and Stacking Techniques

Coastal wetlands are a critical component of the coastal landscape that are increasingly threatened by sea level rise and other human disturbance. Periodically mapping wetland distribution is crucial to coastal ecosystem management. Ensemble algorithms (EL), such as random forest (RF) and gradient boosting machine (GBM) algorithms, are now commonly applied in the field of remote sensing. However, the performance and potential of other EL methods, such as extreme gradient boosting (XGBoost) and bagged trees, are rarely compared and tested for coastal wetland mapping. In this study, we applied the three most widely used EL techniques (i.e., bagging, boosting and stacking) to map wetland distribution in a highly modified coastal catchment, the Manning River Estuary, Australia. Our results demonstrated the advantages of using ensemble classifiers to accurately map wetland types in a coastal landscape. Enhanced bagging decision trees, i.e., classifiers with additional methods to increasing ensemble diversity such as RF and weighted subspace random forest, had comparably high predictive power. For the stacking method evaluated in this study, our results are inconclusive, and further comprehensive quantitative study is encouraged. Our findings also suggested that the ensemble methods were less effective at discriminating minority classes in comparison with more common classes. Finally, the variable importance results indicated that hydro-geomorphic factors, such as tidal depth and distance to water edge, were among the most influential variables across the top classifiers. However, vegetation indices derived from longer time series of remote sensing data that arrest the full features of land phenology are likely to improve wetland type separation in coastal areas.

Remote Sensing of Boreal Wetlands 2: Methods for Evaluating Boreal Wetland Ecosystem State and Drivers of Change

The following review is the second part of a two part series on the use of remotely sensed data for quantifying wetland extent and inferring or measuring condition for monitoring drivers of change on wetland environments. In the first part, we introduce policy makers and non-users of remotely sensed data with an effective feasibility guide on how data can be used. In the current review, we explore the more technical aspects of remotely sensed data processing and analysis using case studies within the literature. Here we describe: (a) current technologies used for wetland assessment and monitoring; (b) the latest algorithmic developments for wetland assessment; (c) new technologies; and (d) a framework for wetland sampling in support of remotely sensed data collection. Results illustrate that high or fine spatial resolution pixels (≤10 m) are critical for identifying wetland boundaries and extent, and wetland class, form and type, but are not required for all wetland sizes. Average accuracies can be up to 11% better (on average) than medium resolution (11–30 m) data pixels when compared with field validation. Wetland size is also a critical factor such that large wetlands may be almost as accurately classified using medium-resolution data (average = 76% accuracy, stdev = 21%). Decision-tree and machine learning algorithms provide the most accurate wetland classification methods currently available, however, these also require sampling of all permutations of variability. Hydroperiod accuracy, which is dependent on instantaneous water extent for single time period datasets does not vary greatly with pixel resolution when compared with field data (average = 87%, 86%) for high and medium resolution pixels, respectively. The results of this review provide users with a guideline for optimal use of remotely sensed data and suggested field methods for boreal and global wetland studies.

Remote Sensing of Boreal Wetlands 1: Data Use for Policy and Management

Wetlands have and continue to undergo rapid environmental and anthropogenic modification and change to their extent, condition, and therefore, ecosystem services. In this first part of a two-part review, we provide decision-makers with an overview on the use of remote sensing technologies for the ‘wise use of wetlands’, following Ramsar Convention protocols. The objectives of this review are to provide: (1) a synthesis of the history of remote sensing of wetlands, (2) a feasibility study to quantify the accuracy of remotely sensed data products when compared with field data based on 286 comparisons found in the literature from 209 articles, (3) recommendations for best approaches based on case studies, and (4) a decision tree to assist users and policymakers at numerous governmental levels and industrial agencies to identify optimal remote sensing approaches based on needs, feasibility, and cost. We argue that in order for remote sensing approaches to be adopted by wetland scientists, land-use managers, and policymakers, there is a need for greater understanding of the use of remote sensing for wetland inventory, condition, and underlying processes at scales relevant for management and policy decisions. The literature review focuses on boreal wetlands primarily from a Canadian perspective, but the results are broadly applicable to policymakers and wetland scientists globally, providing knowledge on how to best incorporate remotely sensed data into their monitoring and measurement procedures. This is the first review quantifying the accuracy and feasibility of remotely sensed data and data combinations needed for monitoring and assessment. These include, baseline classification for wetland inventory, monitoring through time, and prediction of ecosystem processes from individual wetlands to a national scale.

An Optimized Object-Based Random Forest Algorithm for Marsh Vegetation Mapping Using High-Spatial-Resolution GF-1 and ZY-3 Data

Discriminating marsh vegetation is critical for the rapid assessment and management of wetlands. The study area, Honghe National Nature Reserve (HNNR), a typical freshwater wetland, is located in Northeast China. This study optimized the parameters (mtry and ntrees) of an object-based random forest (RF) algorithm to improve the applicability of marsh vegetation classification. Multidimensional datasets were used as the input variables for model training, then variable selection was performed on the variables to eliminate redundancy, which improved classification efficiency and overall accuracy. Finally, the performance of a new generation of Chinese high-spatial-resolution Gaofen-1 (GF-1) and Ziyuan-3 (ZY-3) satellite images for marsh vegetation classification was evaluated using the improved object-based RF algorithm with accuracy assessment. The specific conclusions of this study are as follows: (1) Optimized object-based RF classifications consistently produced more than 70.26% overall accuracy for all scenarios of GF-1 and ZY-3 at the 95% confidence interval. The performance of ZY-3 imagery applied to marsh vegetation mapping is lower than that of GF-1 imagery due to the coarse spatial resolution. (2) Parameter optimization of the object-based RF algorithm effectively improved the stability and classification accuracy of the algorithm. After parameter adjustment, scenario 3 for GF-1 data had the highest classification accuracy of 84% (ZY-3 is 74.72%) at the 95% confidence interval. (3) The introduction of multidimensional datasets improved the overall accuracy of marsh vegetation mapping, but with many redundant variables. Using three variable selection algorithms to remove redundant variables from the multidimensional datasets effectively improved the classification efficiency and overall accuracy. The recursive feature elimination (RFE)-based variable selection algorithm had the best performance. (4) Optical spectral bands, spectral indices, mean value of green and NIR bands in textural information, DEM, TWI, compactness, max difference, and shape index are valuable variables for marsh vegetation mapping. (5) GF-1 and ZY-3 images had higher classification accuracy for forest, cropland, shrubs, and open water.

Automated Mapping of Antarctic Supraglacial Lakes Using a Machine Learning Approach

Supraglacial lakes can have considerable impact on ice sheet mass balance and global sea-level-rise through ice shelf fracturing and subsequent glacier speedup. In Antarctica, the distribution and temporal development of supraglacial lakes as well as their potential contribution to increased ice mass loss remains largely unknown, requiring a detailed mapping of the Antarctic surface hydrological network. In this study, we employ a Machine Learning algorithm trained on Sentinel-2 and auxiliary TanDEM-X topographic data for automated mapping of Antarctic supraglacial lakes. To ensure the spatio-temporal transferability of our method, a Random Forest was trained on 14 training regions and applied over eight spatially independent test regions distributed across the whole Antarctic continent. In addition, we employed our workflow for large-scale application over Amery Ice Shelf where we calculated interannual supraglacial lake dynamics between 2017 and 2020 at full ice shelf coverage. To validate our supraglacial lake detection algorithm, we randomly created point samples over our classification results and compared them to Sentinel-2 imagery. The point comparisons were evaluated using a confusion matrix for calculation of selected accuracy metrics. Our analysis revealed wide-spread supraglacial lake occurrence in all three Antarctic regions. For the first time, we identified supraglacial meltwater features on Abbott, Hull and Cosgrove Ice Shelves in West Antarctica as well as for the entire Amery Ice Shelf for years 2017–2020. Over Amery Ice Shelf, maximum lake extent varied strongly between the years with the 2019 melt season characterized by the largest areal coverage of supraglacial lakes (~763 km2). The accuracy assessment over the test regions revealed an average Kappa coefficient of 0.86 where the largest value of Kappa reached 0.98 over George VI Ice Shelf. Future developments will involve the generation of circum-Antarctic supraglacial lake mapping products as well as their use for further methodological developments using Sentinel-1 SAR data in order to characterize intraannual supraglacial meltwater dynamics also during polar night and independent of meteorological conditions. In summary, the implementation of the Random Forest classifier enabled the development of the first automated mapping method applied to Sentinel-2 data distributed across all three Antarctic regions.