Mapping Plantations in Myanmar by Fusing Landsat-8, Sentinel-2 and Sentinel-1 Data along with Systematic Error Quantification

Coupling optical and SAR imagery for automatic garlic mapping

Accurate garlic identification and mapping are vital for precise crop management and the optimization of yield models. However, previous understandings of garlic identification were limited. Here, we propose an automatic garlic mapping framework using optical and synthetic aperture radar (SAR) images on the Google Earth Engine. Specifically, we firstly mapped winter crops based on the phenology of winter crops derived from Sentinel-2 data. Then, the garlic was identified separately using Sentinel-1 and Sentinel-2 data based on the winter crops map. Additionally, multi-source validation data were used to evaluate our results. In garlic mapping, coupled optical and SAR images (OA 95.34% and kappa 0.91) outperformed the use of only optical images (OA 74.78% and kappa 0.50). The algorithm explored the potential of multi-source remote sensing data to identify target crops in mixed and fragmented planting regions. The garlic planting information from the resultant map is essential for optimizing the garlic planting structure, regulating garlic price fluctuations, and promoting a healthy and sustainable development of the garlic industry.

Google Earth Engine and Artificial Intelligence (AI): A Comprehensive Review

Remote sensing (RS) plays an important role gathering data in many critical domains (e.g., global climate change, risk assessment and vulnerability reduction of natural hazards, resilience of ecosystems, and urban planning). Retrieving, managing, and analyzing large amounts of RS imagery poses substantial challenges. Google Earth Engine (GEE) provides a scalable, cloud-based, geospatial retrieval and processing platform. GEE also provides access to the vast majority of freely available, public, multi-temporal RS data and offers free cloud-based computational power for geospatial data analysis. Artificial intelligence (AI) methods are a critical enabling technology to automating the interpretation of RS imagery, particularly on object-based domains, so the integration of AI methods into GEE represents a promising path towards operationalizing automated RS-based monitoring programs. In this article, we provide a systematic review of relevant literature to identify recent research that incorporates AI methods in GEE. We then discuss some of the major challenges of integrating GEE and AI and identify several priorities for future research. We developed an interactive web application designed to allow readers to intuitively and dynamically review the publications included in this literature review.

The Applicability of LandTrendr to Surface Water Dynamics: A Case Study of Minnesota from 1984 to 2019 Using Google Earth Engine

The means to accurately monitor wetland change over time are crucial to wetland management. This paper explores the applicability of LandTrendr, a temporal segmentation algorithm designed to identify significant interannual trends, to monitor wetlands by modeling surface water presence in Minnesota from 1984 to 2019. A time series of harmonized Landsat and Sentinel-2 data in the spring is developed in Google Earth Engine, and calculated to sub-pixel water fraction. The optimal parameters for modeling this time series with LandTrendr are identified by minimizing omission of known surface water locations, and the result of this optimal model of sub-pixel water fraction is evaluated against reference images and qualitatively. Accuracy of this method is high: overall accuracy is 98% and producer’s and user’s accuracies for inundation are 82% and 88% respectively. Maps summarizing the trendlines of multiple pixels, such as frequency of inundation over the past 35 years, also show LandTrendr as applied here can accurately model long-term trends in surface water presence across wetland types. However, the tendency of omission for more variable prairie pothole wetlands and the under-prediction of inundation for small or emergent wetlands suggests the algorithm will require careful development of the segmented time series to capture inundated conditions more accurately.

A Planted Forest Mapping Method Based on Long-Term Change Trend Features Derived from Dense Landsat Time Series in an Ecological Restoration Region

Planted forests provide a variety of meaningful ecological functions and services, which is a major approach for ecological restoration, especially in arid areas. However, mapping planted forests with remote-sensed data remains challenging due to the similarities in canopy spectral and structure characteristics and associated phenology features between planted forests and other vegetation types. In this study, taking advantage of the Google Earth Engine (GEE) platform and taking the Ningxia Hui Autonomous Region in northwestern China as an example, we developed an approach to map planted forests in an arid region by applying long-term features of the NDVI derived from dense Landsat time series. Our land cover map achieved a satisfactory accuracy and relatively low uncertainty, with an overall accuracy of 93.65% and a kappa value of 0.92. Specifically, the producer (PA) and user accuracies (UA) were 92.48% and 91.79% for the planted forest class, and 93.88% and 95.83% for the natural forest class, respectively. The total planted forest area was estimated as 3608.72 km2 in 2020, accounting for 20.60% of the study area. The proposed mapping approach can facilitate assessment of the restoration effects of ecological engineering and research on ecosystem services and stability of planted forests.

Automated Extraction of Lake Water Bodies in Complex Geographical Environments by Fusing Sentinel-1/2 Data

Lakes are an important component of global water resources. Lake water bodies extraction based on satellite remote sensing mainly utilizes optical or radar data. However, due to the influence of water quality, ground features with low reflectivity, and smooth surface features, it is still challenging to accurately extract water bodies in complex geographic environments. In this work, we proposed a lake water bodies extraction method by fusing Sentinel-1/2 data. Firstly, the proposed method analyzed the difference of the spectral polarization features between water and non-water in complex geographical environment. Then, the spectral polarization and water index were fused to multidimensional features by feature stacking. Finally, support vector machines are used to classify. Six typical lakes (including urban, mountains, and polluted and clean lakes) in China were used to verify the mapping accuracy. The results showed that extracting lake water bodies by fusing Sentinel-1/2 data had a better performance than using optical or radar data solely, all types of lakes achieved better extraction results, the overall accuracy of lake water extraction is improved by 3%, and the error of commission and omission is controlled within 6%. Comparative experiments indicate that combine radar polarization information with spectral information is helpful to improve the accuracy of different types of lakes extraction in complex geographical environment.

Land Use Land Cover Classification with U-Net: Advantages of Combining Sentinel-1 and Sentinel-2 Imagery

The U-net is nowadays among the most popular deep learning algorithms for land use/land cover (LULC) mapping; nevertheless, it has rarely been used with synthetic aperture radar (SAR) and multispectral (MS) imagery. On the other hand, the discrimination between plantations and forests in LULC maps has been emphasized, especially for tropical areas, due to their differences in biodiversity and ecosystem services provision. In this study, we trained a U-net using different imagery inputs from Sentinel-1 and Sentinel-2 satellites, MS, SAR and a combination of both (MS + SAR); while a random forests algorithm (RF) with the MS + SAR input was also trained to evaluate the difference in algorithm selection. The classification system included ten classes, including old-growth and secondary forests, as well as old-growth and young plantations. The most accurate results were obtained with the MS + SAR U-net, where the highest overall accuracy (0.76) and average F1-score (0.58) were achieved. Although MS + SAR and MS U-nets gave similar results for almost all of the classes, for old-growth plantations and secondary forest, the addition of the SAR band caused an F1-score increment of 0.08–0.11 (0.62 vs. 0.54 and 0.45 vs. 0.34, respectively). Consecutively, in comparison with the MS + SAR RF, the MS + SAR U-net obtained higher F1-scores for almost all the classes. Our results show that using the U-net with a combined input of SAR and MS images enabled a higher F1-score and accuracy for a detailed LULC map, in comparison with other evaluated methods.

Automatic Detection of Impervious Surfaces from Remotely Sensed Data Using Deep Learning

The large scale quantification of impervious surfaces provides valuable information for urban planning and socioeconomic development. Remote sensing and GIS techniques provide spatial and temporal information of land surfaces and are widely used for modeling impervious surfaces. Traditionally, these surfaces are predicted by computing statistical indices derived from different bands available in remotely sensed data, such as the Landsat and Sentinel series. More recently, researchers have explored classification and regression techniques to model impervious surfaces. However, these modeling efforts are limited due to lack of labeled data for training and evaluation. This in turn requires significant effort for manual labeling of data and visual interpretation of results. In this paper, we train deep learning neural networks using TensorFlow to predict impervious surfaces from Landsat 8 images. We used OpenStreetMap (OSM), a crowd-sourced map of the world with manually interpreted impervious surfaces such as roads and buildings, to programmatically generate large amounts of training and evaluation data, thus overcoming the need for manual labeling. We conducted extensive experimentation to compare the performance of different deep learning neural network architectures, optimization methods, and the set of features used to train the networks. The four model configurations labeled U-Net_SGD_Bands, U-Net_Adam_Bands, U-Net_Adam_Bands+SI, and VGG-19_Adam_Bands+SI resulted in a root mean squared error (RMSE) of 0.1582, 0.1358, 0.1375, and 0.1582 and an accuracy of 90.87%, 92.28%, 92.46%, and 90.11%, respectively, on the test set. The U-Net_Adam_Bands+SI Model, similar to the others mentioned above, is a deep learning neural network that combines Landsat 8 bands with statistical indices. This model performs the best among all four on statistical accuracy and produces qualitatively sharper and brighter predictions of impervious surfaces as compared to the other models.

Uneven Frontiers: Exposing the Geopolitics of Myanmar’s Borderlands with Critical Remote Sensing

A critical remote sensing approach illuminates the geopolitics of development within Myanmar and across its ethnic minority borderlands. By integrating nighttime light (NTL) data from 1992–2020, long-term ethnographic fieldwork, and a review of scholarly and gray literature, we analyzed how Myanmar’s economic geography defies official policy, attesting to persistent inequality and the complex relationships between state-sponsored and militia-led violence, resource extraction, and trade. While analysis of DMSP-OLS data (1992–2013) and VIIRS data (2013–2020) reveals that Myanmar brightened overall, especially since the 2010s in line with its now-halting liberalization, growth in lights was unequally distributed. Although ethnic minority states brightened more rapidly than urbanized ethnic majority lowland regions, in 2020, the latter still emitted 5.6-fold more radiance per km2. Moreover, between 2013 and 2020, Myanmar’s borderlands were on average just 13% as bright as those of its five neighboring countries. Hot spot analysis of radiance within a 50 km-wide area spanning both sides of the border confirmed that most significant clusters of light lay outside Myanmar. Among the few hot spots on Myanmar’s side, many were associated with official border crossings such as Muse, the formal hub for trade with China, and Tachileik and Myawaddy next to Thailand. Yet some of the most significant increases in illumination between 2013 and 2020 occurred in areas controlled by the Wa United State Party and its army, which are pursuing infrastructure development and mining along the Chinese border from Panghsang to the illicit trade hub of Mongla. Substantial brightening related to the “world’s largest refugee camp” was also detected in Bangladesh, where displaced Rohingya Muslims fled after Myanmar’s military launched a violent crackdown. However, no radiance nor change in radiance were discernible in areas within Myanmar where ethnic cleansing operations occurred, pointing to the limitations of NTL. The diverse drivers and implications of changes in light observed from space emphasize the need for political and economically situated remote sensing.

Mapping Paddy Rice with Sentinel-1/2 and Phenology-, Object-Based Algorithm—A Implementation in Hangjiahu Plain in China Using GEE Platform

In tropical/subtropical monsoon regions, accurate rice mapping is hampered by the following factors: (1) The frequent occurrence of clouds in such areas during the rice-growing season interferes strongly with optical remote sensing observations; (2) The agro-landscape in such regions is fragmented and scattered. Rice maps produced using low spatial resolution data cannot well delineate the detailed distribution of rice, while pixel-based mapping using medium and high resolutions has significant salt-and-pepper noise. (3) The cropping system is complex, and rice has a rotation schedule with other crops. Therefore, the Phenology-, Object- and Double Source-based (PODS) paddy rice mapping algorithm is implemented, which consists of three steps: (1) object extraction from multi-temporal 10-m Sentinel-2 images where the extracted objects (fields) are the basic classification units; (2) specifying the phenological stage of transplanting from Savitzky–Golay filtered enhanced vegetation index (EVI) time series using the PhenoRice algorithm; and (3) the identification of rice objects based on flood signal detection from time-series microwave and optical signals of the Sentinel-1/2. This study evaluated the potential of the combined use of the Sentinel-1/2 mission on paddy rice mapping in monsoon regions with the Hangzhou-Jiaxin-Huzhou (HJH) plain in China as the case study. A cloud computing approach was used to process the available Sentinel-1/2 imagery from 2019 and MODIS images from 2018 to 2020 in the HJH plain on the Google Earth Engine (GEE) platform. An accuracy assessment showed that the resultant object-based paddy rice map has a high accuracy with a producer (user) accuracy of 0.937 (0.926). The resultant 10-m paddy rice map is expected to provide unprecedented detail, spatial distribution, and landscape patterns for paddy rice fields in monsoon regions.

Classification of Nemoral Forests with Fusion of Multi-Temporal Sentinel-1 and 2 Data

Mapping forest extent and forest cover classification are important for the assessment of forest resources in socio-economic as well as ecological terms. Novel developments in the availability of remotely sensed data, computational resources, and advances in areas of statistical learning have enabled the fusion of multi-sensor data, often yielding superior classification results. Most former studies of nemoral forests fusing multi-sensor and multi-temporal data have been limited in spatial extent and typically to a simple classification of landscapes into major land cover classes. We hypothesize that multi-temporal, multi-sensor data will have a specific strength in the further classification of nemoral forest landscapes owing to the distinct seasonal patterns in the phenology of broadleaves. This study aimed to classify the Danish landscape into forest/non-forest and further into forest types (broadleaved/coniferous) and species groups, using a cloud-based approach based on multi-temporal Sentinel 1 and 2 data and a random forest classifier trained with National Forest Inventory (NFI) data. Mapping of non-forest and forest resulted in producer accuracies of 99% and 90%, respectively. The mapping of forest types (broadleaf and conifer) within the forested area resulted in producer accuracies of 95% for conifer and 96% for broadleaf forest. Tree species groups were classified with producer accuracies ranging 34–74%. Species groups with coniferous species were the least confused, whereas the broadleaf groups, especially Quercus species, had higher error rates. The results are applied in Danish national accounting of greenhouse gas emissions from forests, resource assessment, and assessment of forest biodiversity potentials.

A New Machine Learning Approach in Detecting the Oil Palm Plantations Using Remote Sensing Data

The rapid expansion of oil palm is a major driver of deforestation and other associated damage to the climate and ecosystem in tropical regions, especially Southeast Asia. It is therefore necessary to precisely detect and monitor oil palm plantations to safeguard the ecosystem services and biodiversity of tropical forests. Compared with optical data, which are vulnerable to cloud cover, the Sentinel-1 dual-polarization C-band synthetic aperture radar (SAR) acquires global observations under all weather conditions and times of day and shows good performance for oil palm detection in the humid tropics. However, because accurately distinguishing mature and young oil palm trees by using optical and SAR data is difficult and considering the strong dependence on the input parameter values when detecting oil palm plantations by employing existing classification algorithms, we propose an innovative method to improve the accuracy of classifying the oil palm type (mature or young) and detecting the oil palm planting area in Sumatra by fusing Landsat-8 and Sentinel-1 images. We extract multitemporal spectral characteristics, SAR backscattering values, vegetation indices, and texture features to establish different feature combinations. Then, we use the random forest algorithm based on improved grid search optimization (IGSO-RF) and select optimal feature subsets to establish a classification model and detect oil palm plantations. Based on the IGSO-RF classifier and optimal features, our method improved the oil palm detection accuracy and obtained the best model performance (OA = 96.08% and kappa = 0.9462). Moreover, the contributions of different features to oil palm detection are different; nevertheless, the optimal feature subset performed the best and demonstrated good potential for the detection of oil palm plantations.

Synergistic Use of Sentinel-1 and Sentinel-2 to Map Natural Forest and Acacia Plantation and Stand Ages in North-Central Vietnam

Many remote sensing studies do not distinguish between natural and planted forests. We combine C-Band Synthetic Aperture Radar (Sentinel-1, S-1) and optical satellite imagery (Sentinel-2, S-2) and examine Random Forest (RF) classification of acacia plantations and natural forest in North-Central Vietnam. We demonstrate an ability to distinguish plantation from natural forest, with overall classification accuracies of 87% for S-1, and 92.5% and 92.3% for S-2 and for S-1 and S-2 combined respectively. We found that the ratio of the Short-Wave Infrared Band to the Red Band proved most effective in distinguishing acacia from natural forest. We used RF on S-2 imagery to classify acacia plantations into 6 age classes with an overall accuracy of 70%, with young plantation consistently separated from older. However, accuracy was lower at distinguishing between the older age classes. For both distinguishing plantation and natural forest, and determining plantation age, a combination of radar and optical imagery did nothing to improve classification accuracy.

Assessing the Natural Recovery of Mangroves after Human Disturbance Using Neural Network Classification and Sentinel-2 Imagery in Wunbaik Mangrove Forest, Myanmar

In this study, we examined the natural recovery of mangroves in abandoned shrimp ponds located in the Wunbaik Mangrove Forest (WMF) in Myanmar using artificial neural network (ANN) classification and a change detection approach with Sentinel-2 satellite images. In 2020, we conducted various experiments related to mangrove classification by tuning input features and hyper-parameters. The selected ANN model was used with a transfer learning approach to predict the mangrove distribution in 2015. Changes were detected using classification results from 2015 and 2020. Naturally recovering mangroves were identified by extracting the change detection results of three abandoned shrimp ponds selected during field investigation. The proposed method yielded an overall accuracy of 95.98%, a kappa coefficient of 0.92, mangrove and non-mangrove precisions of 0.95 and 0.98, respectively, recalls of 0.96, and F1 scores of 0.96 for the 2020 classification. For the 2015 prediction, transfer learning improved model performance, resulting in an overall accuracy of 97.20%, a kappa coefficient of 0.94, mangrove and non-mangrove precisions of 0.98 and 0.96, respectively, recalls of 0.98 and 0.97, and F1 scores of 0.96. The change detection results showed that mangrove forests in the WMF slightly decreased between 2015 and 2020. Naturally recovering mangroves were detected at approximately 50% of each abandoned site within a short abandonment period. This study demonstrates that the ANN method using Sentinel-2 imagery and topographic and canopy height data can produce reliable results for mangrove classification. The natural recovery of mangroves presents a valuable opportunity for mangrove rehabilitation at human-disturbed sites in the WMF.

Combination of Landsat 8 OLI and Sentinel-1 SAR Time-Series Data for Mapping Paddy Fields in Parts of West and Central Java Provinces, Indonesia

The rise of Google Earth Engine, a cloud computing platform for spatial data, has unlocked seamless integration for multi-sensor and multi-temporal analysis, which is useful for the identification of land-cover classes based on their temporal characteristics. Our study aims to employ temporal patterns from monthly-median Sentinel-1 (S1) C-band synthetic aperture radar data and cloud-filled monthly spectral indices, i.e., Normalized Difference Vegetation Index (NDVI), Modified Normalized Difference Water Index (MNDWI), and Normalized Difference Built-up Index (NDBI), from Landsat 8 (L8) OLI for mapping rice cropland areas in the northern part of Central Java Province, Indonesia. The harmonic function was used to fill the cloud and cloud-masked values in the spectral indices from Landsat 8 data, and smile Random Forests (RF) and Classification And Regression Trees (CART) algorithms were used to map rice cropland areas using a combination of monthly S1 and monthly harmonic L8 spectral indices. An additional terrain variable, Terrain Roughness Index (TRI) from the SRTM dataset, was also included in the analysis. Our results demonstrated that RF models with 50 (RF50) and 80 (RF80) trees yielded better accuracy for mapping the extent of paddy fields, with user accuracies of 85.65% (RF50) and 85.75% (RF80), and producer accuracies of 91.63% (RF80) and 93.48% (RF50) (overall accuracies of 92.10% (RF80) and 92.47% (RF50)), respectively, while CART yielded a user accuracy of only 84.83% and a producer accuracy of 80.86%. The model variable importance in both RF50 and RF80 models showed that vertical transmit and horizontal receive (VH) polarization and harmonic-fitted NDVI were identified as the top five important variables, and the variables representing February, April, June, and December contributed more to the RF model. The detection of VH and NDVI as the top variables which contributed up to 51% of the Random Forest model indicated the importance of the multi-sensor combination for the identification of paddy fields.

A Multi Sensor Approach to Forest Type Mapping for Advancing Monitoring of Sustainable Development Goals (SDG) in Myanmar

Monitoring forests is important for measuring overall success of the 2030 Agenda because forests play an essential role in meeting many Sustainable Development Goals (SDG), especially SDG 15. Our study evaluates the contribution of three satellite data sources (Landsat-8, Sentinel-2 and Sentinel-1) for mapping diverse forest types in Myanmar. This assessment is especially important because Myanmar is currently revising its classification system for forests and it is critical that these new forest types can be accurately mapped and monitored over time using satellite imagery. Our results show that using a combination of Sentinel-1 and Sentinel-2 yields the highest accuracy (89.6% ± 0.16 percentage point(pp)), followed by Sentinel-2 alone (87.97% ± 0.11 pp) and Landsat-8 (82.68% ± 0.13 pp). The higher spatial resolution of Sentinel-2 Blue, Green, Red, Narrow Near Infrared and Short Wave Infrared bands enhances accuracy by 4.83% compared to Landsat-8. The addition of the Sentinel-2 Near Infrared and three Vegetation Red Edge bands further improve accuracy by 0.46% compared to using only Sentinel-2 Blue, Green, Red, Narrow Near Infrared and Short Wave Infrared bands. Adding the radar information from Sentinel-1 further increases the accuracy by 1.63%. We were able to map the two major forest types, Upper Moist and Upper Dry Mixed Deciduous Forest, which comprise 90% of our study area. Accuracies for these forest types ranged from 77 to 96% depending on the sensors used, demonstrating the feasibility of using satellite data to map forest categories from a newly revised classification system. Our results advance the ongoing development of the National Forest Monitoring System (NFMS) by the Myanmar Forest Department and United Nations-Food and Agriculture Organization (UN-FAO) and facilitates future monitoring of progress towards the SDGs.

Recent Applications of Landsat 8/OLI and Sentinel-2/MSI for Land Use and Land Cover Mapping: A Systematic Review

Recent applications of Landsat 8 Operational Land Imager (L8/OLI) and Sentinel-2 MultiSpectral Instrument (S2/MSI) data for acquiring information about land use and land cover (LULC) provide a new perspective in remote sensing data analysis. Jointly, these sources permit researchers to improve operational classification and change detection, guiding better reasoning about landscape and intrinsic processes, as deforestation and agricultural expansion. However, the results of their applications have not yet been synthesized in order to provide coherent guidance on the effect of their applications in different classification processes, as well as to identify promising approaches and issues which affect classification performance. In this systematic review, we present trends, potentialities, challenges, actual gaps, and future possibilities for the use of L8/OLI and S2/MSI for LULC mapping and change detection. In particular, we highlight the possibility of using medium-resolution (Landsat-like, 10–30 m) time series and multispectral optical data provided by the harmonization between these sensors and data cube architectures for analysis-ready data that are permeated by publicizations, open data policies, and open science principles. We also reinforce the potential for exploring more spectral bands combinations, especially by using the three Red-edge and the two Near Infrared and Shortwave Infrared bands of S2/MSI, to calculate vegetation indices more sensitive to phenological variations that were less frequently applied for a long time, but have turned on since the S2/MSI mission. Summarizing peer-reviewed papers can guide the scientific community to the use of L8/OLI and S2/MSI data, which enable detailed knowledge on LULC mapping and change detection in different landscapes, especially in agricultural and natural vegetation scenarios.

A Comparison of Three Temporal Smoothing Algorithms to Improve Land Cover Classification: A Case Study from NEPAL

Time series land cover data statistics often fluctuate abruptly due to seasonal impact and other noise in the input image. Temporal smoothing techniques are used to reduce the noise in time series data used in land cover mapping. The effects of smoothing may vary based on the smoothing method and land cover category. In this study, we compared the performance of Fourier transformation smoothing, Whittaker smoother and Linear-Fit averaging smoother on Landsat 5, 7 and 8 based yearly composites to classify land cover in Province No. 1 of Nepal. The performance of each smoother was tested based on whether it was applied on image composites or on land cover primitives generated using the random forest machine learning method. The land cover data used in the study was from the years 2000 to 2018. Probability distribution was examined to check the quality of primitives and accuracy of the final land cover maps were accessed. The best results were found for the Whittaker smoothing for stable classes and Fourier smoothing for other classes. The results also show that classification using a properly selected smoothing algorithm outperforms a classification based on its unsmoothed data set. The final land cover generated by combining the best results obtained from different smoothing approaches increased our overall land cover map accuracy from 79.18% to 83.44%. This study shows that smoothing can result in a substantial increase in the quality of the results and that the smoothing approach should be carefully considered for each land cover class.

New JAXA High-Resolution Land Use/Land Cover Map for Vietnam Aiming for Natural Forest and Plantation Forest Monitoring

Highly detailed and accurate forest maps are important for various applications including forest monitoring, forestry policy, climate change, and biodiversity loss. This study demonstrates a comprehensive and geographically transferable approach to produce a 12 category high-resolution land use/land cover (LULC) map over mainland Vietnam in 2016 by remote sensing data. The map included several natural forest categories (evergreen broadleaf, deciduous (mostly deciduous broadleaf), and coniferous (mostly evergreen coniferous)) and one category representing all popular plantation forests in Vietnam such as acacia (Acacia mangium, Acacia auriculiformis, Acacia hybrid), eucalyptus (Eucalyptus globulus), rubber (Hevea brasiliensis), and others. The approach combined the advantages of various sensor data by integrating their posterior probabilities resulting from applying a probabilistic classifier (comprised of kernel density estimation and Bayesian inference) to each datum individually. By using different synthetic aperture radar (SAR) images (PALSAR-2/ScanSAR, PALSAR-2 mosaic, Sentinel-1), optical images (Sentinel-2, Landsat-8) and topography data (AW3D30), the resultant map achieved 85.6% for the overall accuracy. The major forest classes including evergreen broadleaf forests and plantation forests had a user’s accuracy and producer’s accuracy ranging from 86.0% to 95.3%. Our map identified 9.55 × 106 ha (±0.16 × 106 ha) of natural forests and 3.89 × 106 ha (±0.11 × 106 ha) of plantation forests over mainland Vietnam, which were close to the Vietnamese government’s statistics (with differences of less than 8%). This study’s result provides a reliable input/reference to support forestry policy and land sciences in Vietnam.

Comparing Sentinel-1 Surface Water Mapping Algorithms and Radiometric Terrain Correction Processing in Southeast Asia Utilizing Google Earth Engine

Satellite remote sensing plays an important role in the monitoring of surface water for historical analysis and near real-time applications. Due to its cloud penetrating capability, many studies have focused on providing efficient and high quality methods for surface water mapping using Synthetic Aperture Radar (SAR). However, few studies have explored the effects of SAR pre-processing steps used and the subsequent results as inputs into surface water mapping algorithms. This study leverages the Google Earth Engine to compare two unsupervised histogram-based thresholding surface water mapping algorithms utilizing two distinct pre-processed Sentinel-1 SAR datasets, specifically one with and one without terrain correction. The resulting surface water maps from the four different collections were validated with user-interpreted samples from high-resolution Planet Scope data. It was found that the overall accuracy from the four collections ranged from 92% to 95% with Cohen’s Kappa coefficients ranging from 0.7999 to 0.8427. The thresholding algorithm that samples a histogram based on water edge information performed best with a maximum accuracy of 95%. While the accuracies varied between methods it was found that there is no statistical significant difference between the errors of the different collections. Furthermore, the surface water maps generated from the terrain corrected data resulted in a intersection over union metrics of 95.8%–96.4%, showing greater spatial agreement, as compared to 92.3%–93.1% intersection over union using the non-terrain corrected data. Overall, it was found that algorithms using terrain correction yield higher overall accuracy and yielded a greater spatial agreement between methods. However, differences between the approaches presented in this paper were not found to be significant suggesting both methods are valid for generating accurate surface water maps. High accuracy surface water maps are critical to disaster planning and response efforts, thus results from this study can help inform SAR data users on the pre-processing steps needed and its effects as inputs on algorithms for surface water mapping applications.

Predictive Analytics for Identifying Land Cover Change Hotspots in the Mekong Region

Understanding land cover change dynamics and potential pathways of change is of critical importance for sustainable resource management, to promote food security and resilience on a range of spatial scales. Data scarcity is a key concern, however, with the availability of free Earth Observation (EO) data, such challenges can be suitably addressed. In this research we have developed a robust machine learning (random forest) approach utilizing EO and Geographic Information System (GIS) data, which enables an innovative means for our simulations to be driven only by historical drivers of change and hotspot prediction based on probability to change. We used the Mekong region as a case study to generate a training and validation sample from historical land cover patterns of change and used this information to train a random forest machine learning model. Data samples were created from the SERVIR-Mekong land cover data series. Data sets were created for 2 categories both containing 8 classes. The 2 categories included—any generic class to change into a specific one and vice versa. Classes included the following: Aquaculture; Barren; Cropland; Flooded Forest; Mangroves; Forest; Plantations; Wetlands; and Urban. The training points were used to sample a series of satellite-derived surface reflectance products and other data layers such as information on slope, distance to road and census data, which represent the drivers of change. The classifier was trained in binary mode and showed a clear separation between change and no change. An independent validation dataset of historical change pixels show that all median change probabilities are greater than 80% and all lower quantiles, except one, are greater than 70%. The 2018 probability change maps show high probabilities for the Plantations and Forest classes in the ‘Generic to Specific’ and ’Specific to generic’ category, respectively. A time-series analysis of change probability shows that forests have become more likely to convert into other classes during the last two decades, across all countries. We successfully demonstrated that historical change patters combined with big data and machine learning technologies are powerful tools for predictive change analytics on a planetary scale.

Harmonization of Landsat and Sentinel 2 for Crop Monitoring in Drought Prone Areas: Case Studies of Ninh Thuan (Vietnam) and Bekaa (Lebanon)

Proper satellite-based crop monitoring applications at the farm-level often require near-daily imagery at medium to high spatial resolution. The combination of data from different ongoing satellite missions Sentinel 2 (ESA) and Landsat 7/8 (NASA) provides this unprecedented opportunity at a global scale; however, this is rarely implemented because these procedures are data demanding and computationally intensive. This study developed a robust stream processing for the harmonization of Landsat 7, Landsat 8 and Sentinel 2 in the Google Earth Engine cloud platform, connecting the benefit of coherent data structure, built-in functions and computational power in the Google Cloud. The harmonized surface reflectance images were generated for two agricultural schemes in Bekaa (Lebanon) and Ninh Thuan (Vietnam) during 2018–2019. We evaluated the performance of several pre-processing steps needed for the harmonization including the image co-registration, Bidirectional Reflectance Distribution Functions correction, topographic correction, and band adjustment. We found that the misregistration between Landsat 8 and Sentinel 2 images varied from 10 m in Ninh Thuan (Vietnam) to 32 m in Bekaa (Lebanon), and posed a great impact on the quality of the final harmonized data set if not treated. Analysis of a pair of overlapped L8-S2 images over the Bekaa region showed that, after the harmonization, all band-to-band spatial correlations were greatly improved. Finally, we demonstrated an application of the dense harmonized data set for crop mapping and monitoring. An harmonic (Fourier) analysis was applied to fit the detected unimodal, bimodal and trimodal shapes in the temporal NDVI patterns during one crop year in Ninh Thuan province. The derived phase and amplitude values of the crop cycles were combined with max-NDVI as an R-G-B false composite image. The final image was able to highlight croplands in bright colors (high phase and amplitude), while the non-crop areas were shown with grey/dark (low phase and amplitude). The harmonized data sets (with 30 m spatial resolution) along with the Google Earth Engine scripts used are provided for public use.

Assessing the Importance of Tree Cover Threshold for Forest Cover Mapping Derived from Global Forest Cover in Myanmar

Comprehensive forest cover mapping is essential for making policy and management decisions. However, creating a forest cover map from raw remote sensing data is a barrier for many users. Here, we investigated the effects of different tree cover thresholds on the accuracy of forest cover maps derived from the Global Forest Change Dataset (GFCD) across different ecological zones in a country-scale evaluation of Myanmar. To understand the effect of different thresholds on map accuracy, nine forest cover maps having thresholds ranging from 10% to 90% were created from the GFCD. The accuracy of the forest cover maps within each ecological zone and at the national scale was assessed. The overall accuracies of ecological zones other than tropical rainforest were highest when the threshold for tree cover was less than 50%. The appropriate threshold for tropical rainforests was 80%. Therefore, different optimal tree cover thresholds were required to achieve the highest overall accuracy depending on ecological zones. However, in the unique case of Myanmar, we were able to determine the threshold across the whole country. We concluded that the threshold for tree cover for creating a forest cover map should be determined according to the areal ratio of ecological zones determined from large-scale monitoring. Our results are applicable to tropical regions having similar ecological zones.

Automatic Detection of Spatiotemporal Urban Expansion Patterns by Fusing OSM and Landsat Data in Kathmandu

During the last few decades, a large number of people have migrated to Kathmandu city from all parts of Nepal, resulting in rapid expansion of the city. The unplanned and accelerated growth is causing many environmental and population management issues. To manage urban growth efficiently, the city authorities need a means to be able to monitor urban expansion regularly. In this study, we introduced a novel approach to automatically detect urban expansion by leveraging state-of-the-art cloud computing technologies using the Google Earth Engine (GEE) platform. We proposed a new index named Normalized Difference and Distance Built-up Index (NDDBI) for identifying built-up areas by combining the LandSat-derived vegetation index with distances from the nearest roads and buildings analysed from OpenStreetMap (OSM). We also focused on logical consistencies of land-cover change to remove unreasonable transitions supported by the repeat photography. Our analysis of the historical urban growth patterns between 2000 and 2018 shows that the settlement areas were increased from 63.68 sq km in 2000 to 148.53 sq km in 2018. The overall accuracy of mapping the newly-built areas of urban expansion was 94.33%. We have demonstrated that the methodology and data generated in the study can be replicated to easily map built-up areas and support quicker and more efficient land management and land-use planning in rapidly growing cities worldwide.

Oil palm concessions in southern Myanmar consist mostly of unconverted forest

The increased demand for palm oil has led to an expansion of oil palm concessions in the tropics, and the clearing of abundant forest as a result. However, concessions are typically incompletely planted to varying degrees, leaving much land unused. The remaining forests within such concessions are at high risk of deforestation, as there are normally no legal hurdles to their clearance, therefore making them excellent targets for conservation. We investigated the location of oil palm plantations and the other major crop – rubber plantations in southern Myanmar, and compared them to concession boundaries. Our results show that rubber plantations cover much larger areas than oil palm in the region, indicating that rubber is the region’s preferred crop. Furthermore, only 15% of the total concession area is currently planted with oil palm (49,000 ha), while 25,000 ha is planted outside concession boundaries. While this may in part be due to uncertain and/or changing boundaries, this leaves most of the concession area available for other land uses, including forest conservation and communities’ livelihood needs. Reconsidering the remaining concession areas can also significantly reduce future emission risks from the region.

Detecting Forest Changes Using Dense Landsat 8 and Sentinel-1 Time Series Data in Tropical Seasonal Forests

The accurate and timely detection of forest disturbances can provide valuable information for effective forest management. Combining dense time series observations from optical and synthetic aperture radar satellites has the potential to improve large-area forest monitoring. For various disturbances, machine learning algorithms might accurately characterize forest changes. However, there is limited knowledge especially on the use of machine learning algorithms to detect forest disturbances through hybrid approaches that combine different data sources. This study investigated the use of dense Landsat 8 and Sentinel-1 time series data for detecting disturbances in tropical seasonal forests based on a machine learning algorithm. The random forest algorithm was used to predict the disturbance probability of each Landsat 8 and Sentinel-1 observation using variables derived from a harmonic regression model, which characterized seasonality and disturbance-related changes. The time series disturbance probabilities of both sensors were then combined to detect forest disturbances in each pixel. The results showed that the combination of Landsat 8 and Sentinel-1 achieved an overall accuracy of 83.6% for disturbance detection, which was higher than the disturbance detection using only Landsat 8 (78.3%) or Sentinel-1 (75.5%). Additionally, more timely disturbance detection was achieved by combining Landsat 8 and Sentinel-1. Small-scale disturbances caused by logging led to large omissions of disturbances; however, other disturbances were detected with relatively high accuracy. Although disturbance detection using only Sentinel-1 data had low accuracy in this study, the combination with Landsat 8 data improved the accuracy of detection, indicating the value of dense Landsat 8 and Sentinel-1 time series data for timely and accurate disturbance detection.