Modeling and estimating aboveground biomass of Dacrydium pierrei in China using machine learning with climate change

Ecosystem feedbacks constrain the effect of day-to-day weather variability on land-atmosphere carbon exchange

Whole-ecosystem interactions and feedbacks constrain ecosystem responses to environmental change. The effects of these constraints on responses to climate trends and extreme weather events have been well studied. Here we examine how these constraints respond to changes in day-to-day weather variability without changing the long-term mean weather. Although environmental variability is recognized as a critical factor affecting ecological function, the effects of climate change on day-to-day weather variability and the resultant impacts on ecosystem function are still poorly understood. Changes in weather variability can alter the mean rates of individual ecological processes because many processes respond non-linearly to environmental drivers. We assessed how these individual-process responses to changes in day-to-day weather variability interact with one another at an ecosystem level. We examine responses of arctic tundra to changes in weather variability using stochastic simulations of daily temperature, precipitation, and light to drive a biogeochemical model. Changes in weather variability altered ecosystem carbon, nitrogen, and phosphorus stocks and cycling rates in our model. However, responses of some processes (e.g., respiration) were inconsistent with expectations because ecosystem feedbacks can moderate, or even reverse, direct process responses to weather variability. More weather variability led to greater carbon losses from land to atmosphere; less variability led to higher carbon sequestration on land. The magnitude of modeled ecosystem response to weather variability was comparable to that predicted for the effects of climate mean trends by the end of the century.

A research landscape bibliometric analysis on climate change for last decades: Evidence from applications of machine learning

Climate change (CC) is one of the greatest threats to human health, safety, and the environment. Given its current and future impacts, numerous studies have employed computational tools (e.g., machine learning, ML) to understand, mitigate, and adapt to CC. Therefore, this paper seeks to comprehensively analyze the research/publications landscape on the MLCC research based on published documents from Scopus. The high productivity and research impact of MLCC has produced highly cited works categorized as science, technology, and engineering to the arts, humanities, and social sciences. The most prolific author is Shamsuddin Shahid (based at Universiti Teknologi Malaysia), whereas the Chinese Academy of Sciences is the most productive affiliation on MLCC research. The most influential countries are the United States and China, which is attributed to the funding activities of the National Science Foundation and the National Natural Science Foundation of China (NSFC), respectively. Collaboration through co-authorship in high-impact journals such as Remote Sensing was also identified as an important factor in the high rate of productivity among the most active stakeholders researching MLCC topics worldwide. Keyword co-occurrence analysis identified four major research hotspots/themes on MLCC research that describe the ML techniques, potential risky sectors, remote sensing, and sustainable development dynamics of CC. In conclusion, the paper finds that MLCC research has a significant socio-economic, environmental, and research impact, which points to increased discoveries, publications, and citations in the near future.

Impacts of extreme agroclimatic indicators on the performance of coffee (Coffea arabica L.) aboveground biomass in Jimma Zone, Ethiopia

Estimating crop biomass is critical for countries whose primary source of income is agriculture. It is a valuable indicator for evaluating crop yields and provides information to growers and managers for developing climate change adaptation strategies. The objective of the study was to model the impacts of agroclimatic indicators on the performance of aboveground biomass (AGB) in Arabica coffee trees, a critical income source for millions of Ethiopians. One hundred thirty-five coffee tree stump diameters were measured at 40 cm above ground level. The historical (1998–2010) and future (2041–2070) agroclimatic data were downloaded from the European Copernicus climate change services website. All datasets were tested for missing data, outliers, and multicollinearity and were grouped into three clusters using the K-mean clustering method. The parameter estimates (coefficients of regression) were analyzed using a generalized regression model. The performance of coffee trees' AGB in each cluster was estimated using an artificial neural network model. The future expected change in AGB of coffee trees was compared using a paired t-test. The regression model’s results reveal that the sensitivity of C. arabica to agroclimatic variables significantly differs based on the kind of indicator, RCP scenario, and microclimate. Under the current climatic conditions, the rise of the coldest minimum (TNn) and warmest (TXx) temperatures raises the AGB of the coffee tree, but the rise of the warmest minimum (TNx) and coldest maximum (TXn) temperatures decreased it (P < 0.05). Under the RCP4.5, the rise of consecutively dry days (CDD) and TNx would increase the AGB of the coffee tree, while TNx and TXx would decrease it (P < 0.05). Except for TXx, all indicators would significantly reduce the AGB of coffee trees under RCP8.5 (P < 0.05). The average values of AGB under the current, RCP4.5, and RCP85 climate change scenarios, respectively, were 26.66, 28.79, and 24.41 kg/tree. The predicted values of AGB under RCP4.5 and RCP8.5 will be higher in the first and third clusters and lower in the second cluster in the 2060s compared to the current climatic conditions. As a result, early warning systems and adaptive strategies will be necessary to reduce the detrimental consequences of climate change. More research into the effects of other climatic conditions on crops, such as physiologically effective degree days, cold, hot, and rainy periods, is also required.

Quantifying the Effects of Stand and Climate Variables on Biomass of Larch Plantations Using Random Forests and National Forest Inventory Data in North and Northeast China

The accurate estimation of forest biomass is crucial for supporting climate change mitigation efforts such as sustainable forest management. Although traditional regression models have been widely used to link stand biomass with biotic and abiotic predictors, this approach has several disadvantages, including the difficulty in dealing with data autocorrelation, model selection, and convergence. While machine learning can overcome these challenges, the application remains limited, particularly at a large scale with consideration of climate variables. This study used the random forests (RF) algorithm to estimate stand aboveground biomass (AGB) and total biomass (TB) of larch (Larix spp.) plantations in north and northeast China and quantified the contributions of different predictors. The data for modelling biomass were collected from 445 sample plots of the National Forest Inventory (NFI). A total of 22 independent variables (6 stand and 16 climate variables) were used to develop and train climate-sensitive stand biomass models. Optimization of hyper parameters was implemented using grid search and 10-fold cross-validation. The coefficient of determination (R2) and root mean square error (RMSE) of the RF models were 0.9845 and 3.8008 t ha−1 for AGB, and 0.9836 and 5.1963 t ha−1 for TB. The cumulative contributions of stand and climate factors to stand biomass were >98% and <2%, respectively. The most crucial stand and climate variables were stand volume and annual heat-moisture index (AHM), with relative importance values of >60% and ~0.25%, respectively. The partial dependence plots illustrated the complicated relationships between climate factors and stand biomass. This study illustrated the power of RF for estimating stand biomass and understanding the effects of stand and climate factors on forest biomass. The application of RF can be useful for mapping of large-scale carbon stock.

A Novel Method for Estimating Spatial Distribution of Forest Above-Ground Biomass Based on Multispectral Fusion Data and Ensemble Learning Algorithm

Optical remote sensing technology has been widely used in forest resources inventory. Due to the influence of satellite orbits, sensor parameters, sensor errors, and atmospheric effects, there are great differences in vegetation spectral information captured by different satellite sensor images. Spectral fusion technology can couple the advantages of different multispectral sensor images to produce new multispectral data with high spatial and spectral resolution, it has great potential for improving the spectral sensitivity of forest vegetation and alleviating the spectral saturation. However, how to quickly and effectively select the multi-spectral fusion data suitable for forest above-ground biomass (AGB) estimation is a very critical issue. This study proposes a scheme (RF-S) to comprehensively evaluate multispectral fused images and develop the appropriate model for forest AGB estimation, on the basis of random forest (RF) and the stacking ensemble algorithm. First, four classic fusion methods are used to fuse the preprocessed GaoFen-2 (GF-2) multispectral image with Sentinel-2 image to generate 12 fused Sentinel-like images. Secondly, we apply a comprehensive evaluation method to quickly select the optimal fused image for the follow-up research. Subsequently, two feature combination optimization methods are used to select feature variables from the three feature sets. Finally, the stacking ensemble algorithm based on model dynamic integration and hyperparameter automatic optimization, as well as some classic machine learners, are used to construct the forest AGB estimation model. The results show that the fused image NND_B3 (based on nearest neighbor diffusion pan sharpening method and Band3_Red) selected by the evaluation method proposed in this study has the best performance in AGB estimation. Using the stacking ensemble method and NND_B3 image, we get the highest estimation accuracy, with the adjusted R2 and relative root mean square error (RMSEr) of 0.6306 and 15.53%, respectively. The AGB estimation RMSEr of NND_B3 is 19.95% and 24.90% lower than those of GF-2 and Sentinel-2, respectively. We also found that the multi-window texture factor has better performance in the area with low AGB, and it can suppress the overestimation significantly. The AGB spatial distribution estimated using the NND_B3 image matches the field observations well, indicating that the multispectral fusion image combined with the Stacking algorithm can increase the accuracy and saturation of the AGB estimates.

Coniferous Plantations Growing Stock Volume Estimation Using Advanced Remote Sensing Algorithms and Various Fused Data

Spatial distribution prediction of growing stock volume (GSV) for supporting the sustainable management of forest ecosystems, is one of the most widespread applications of remote sensing. For this purpose, remote sensing data were used as predictor variables in combination with ground data obtained from field sample plots. However, with the increase in forest GSV values, the spectral reflectance of remote sensing imagery is often saturated or less sensitive to the GSV changes, making accurate estimation difficult. To improve this, we examined the GSV estimation performance and data saturation of four optical remote sensing image datasets (Landsat 8, Sentinel-2, ZiYuan-3, and GaoFen-2) in the subtropical region of Central South China. First, various feature variables were extracted and three optimization methods were used to select optimal feature variable combinations. Subsequently, k-nearest-neighbor (kNN), random forest regression, and categorical boosting algorithms were employed to build the GSV estimation models, and evaluate the GSV estimation accuracy and saturation. Second, Gram Schmidt (GS) and NNDiffuse pan sharpening (NND) methods were employed to fuse the optimal multispectral images and explore various image fusion schemes suitable for GSV estimation. We proposed an adaptive stacking (AdaStacking) model ensemble algorithm to further improve GSV estimation performance. The results indicated that Sentinel-2 had the highest GSV estimation accuracy exhibiting a minimum relative root mean square error of 20.06% and saturation of 434 m3/ha, followed by GaoFen-2 with a minimum relative root mean square error of 22.16% and a saturation of 409 m3/ha. Among the four fusion images, the NND-B2 image—obtained by fusing the GaoFen-2 green band and Sentinel-2 multispectral image with the NND method—had the best estimation accuracy. The estimated optimal RMSEs of NND-B2 were 24.4% and 16.5% lower than those of GaoFen-2 and Sentinel-2, respectively. Therefore, the fused image data based on GF-2 and Sentinel-2 can effectively couple the advantages of the two images and significantly improve the GSV estimation performance. Moreover, the proposed adaptive stacking model is more effective in GSV estimation than a single model. The GSV estimation saturation value of the AdaStacking model based on NND-B2 was 5.4% higher than that of the KNN-Maha model. The GSV distribution map estimated by AdaStacking model used the NND-B2 dataset corresponded accurately with the field observations. This study provides some insights into the optical image fusion scheme, feature selection, and adaptive modeling algorithm in GSV estimation for coniferous forest.

A novel approach for estimation of aboveground biomass of a carbon-rich mangrove site in India

Mangroves can play a crucial part in climate change mitigation policies due to their high carbon-storing capacity. However, the carbon sequestration potential of Indian mangroves generally remained unexplored to date. In this study, multi-temporal Sentinel-1 and 2 data-derived variables were used to estimate the AGB of a tropical carbon-rich mangrove forest of India. Ensemble prediction of multiple machine learning algorithms, including Random Forest (RF), Gradient Boosted Model (GBM), and Extreme Gradient Boosting (XGB), were used for AGB prediction. The multi-temporal dataset was used in two different ways to find the most suitable method of using them. The results of the analysis showed that the modeling field measured AGB with individual date data values results in estimates with root mean square errors (RMSE) ranging from 149.242 t/ha for XGB to 151.149 t/ha for the RF. Modeling AGB with the average and percentile metrics of the multi-temporal image stack improves the prediction accuracy of AGB, with RMSE ranging from 81.882 t/ha for the XGB to 74.493 t/ha for the RF. The AGB modeling using ensemble prediction showed further improvement in accuracy with an RMSE of 72.864 t/ha and normalized RMSE of 11.38%. In this study, the intra-seasonal variation of Sentinel-1 and 2 data for mangrove ecosystems was explored for the first time. The variations in remotely sensed variables could be attributed mainly to soil moisture availability and rainfall in the mangrove ecosystem. The efficiency of Sentinel-1 and 2 data-derived variables and ensemble prediction of machine learning models for Indian mangroves were also explored for the first time. The methodologies established in this study can be used in the future for accurate prediction and repeated monitoring of AGB for mangrove ecosystems.

Mapping the Growing Stem Volume of the Coniferous Plantations in North China Using Multispectral Data from Integrated GF-2 and Sentinel-2 Images and an Optimized Feature Variable Selection Method

Accurate measurement of forest growing stem volume (GSV) is important for forest resource management and ecosystem dynamics monitoring. Optical remote sensing imagery has great application prospects in forest GSV estimation on regional and global scales as it is easily accessible, has a wide coverage, and mature technology. However, their application is limited by cloud coverage, data stripes, atmospheric effects, and satellite sensor errors. Combining multi-sensor data can reduce such limitations as it increases the data availability, but also causes the multi-dimensional problem that increases the difficulty of feature selection. In this study, GaoFen-2 (GF-2) and Sentinel-2 images were integrated, and feature variables and data scenarios were derived by a proposed adaptive feature variable combination optimization (AFCO) program for estimating the GSV of coniferous plantations. The AFCO algorithm was compared to four traditional feature variable selection methods, namely, random forest (RF), stepwise random forest (SRF), fast iterative feature selection method for k-nearest neighbors (KNN-FIFS), and the feature variable screening and combination optimization procedure based on the distance correlation coefficient and k-nearest neighbors (DC-FSCK). The comparison indicated that the AFCO program not only considered the combination effect of feature variables, but also optimized the selection of the first feature variable, error threshold, and selection of the estimation model. Furthermore, we selected feature variables from three datasets (GF-2, Sentinel-2, and the integrated data) following the AFCO and four other feature selection methods and used the k-nearest neighbors (KNN) and random forest regression (RFR) to estimate the GSV of coniferous plantations in northern China. The results indicated that the integrated data improved the GSV estimation accuracy of coniferous plantations, with relative root mean square errors (RMSErs) of 15.0% and 19.6%, which were lower than those of GF-2 and Sentinel-2 data, respectively. In particular, the texture feature variables derived from GF-2 red band image have a significant impact on GSV estimation performance of the integrated dataset. For most data scenarios, the AFCO algorithm gained more accurate GSV estimates, as the RMSErs were 30.0%, 23.7%, 17.7%, and 17.5% lower than those of RF, SRF, KNN-FIFS, and DC-FSCK, respectively. The GSV distribution map obtained by the AFCO method and RFR model matched the field observations well. This study provides some insight into the application of optical images, optimization of the feature variable combination, and modeling algorithm selection for estimating the GSV of coniferous plantations.

Combination of Feature Selection and CatBoost for Prediction: The First Application to the Estimation of Aboveground Biomass

Increasing numbers of explanatory variables tend to result in information redundancy and “dimensional disaster” in the quantitative remote sensing of forest aboveground biomass (AGB). Feature selection of model factors is an effective method for improving the accuracy of AGB estimates. Machine learning algorithms are also widely used in AGB estimation, although little research has addressed the use of the categorical boosting algorithm (CatBoost) for AGB estimation. Both feature selection and regression for AGB estimation models are typically performed with the same machine learning algorithm, but there is no evidence to suggest that this is the best method. Therefore, the present study focuses on evaluating the performance of the CatBoost algorithm for AGB estimation and comparing the performance of different combinations of feature selection methods and machine learning algorithms. AGB estimation models of four forest types were developed based on Landsat OLI data using three feature selection methods (recursive feature elimination (RFE), variable selection using random forests (VSURF), and least absolute shrinkage and selection operator (LASSO)) and three machine learning algorithms (random forest regression (RFR), extreme gradient boosting (XGBoost), and categorical boosting (CatBoost)). Feature selection had a significant influence on AGB estimation. RFE preserved the most informative features for AGB estimation and was superior to VSURF and LASSO. In addition, CatBoost improved the accuracy of the AGB estimation models compared with RFR and XGBoost. AGB estimation models using RFE for feature selection and CatBoost as the regression algorithm achieved the highest accuracy, with root mean square errors (RMSEs) of 26.54 Mg/ha for coniferous forest, 24.67 Mg/ha for broad-leaved forest, 22.62 Mg/ha for mixed forests, and 25.77 Mg/ha for all forests. The combination of RFE and CatBoost had better performance than the VSURF–RFR combination in which random forests were used for both feature selection and regression, indicating that feature selection and regression performed by a single machine learning algorithm may not always ensure optimal AGB estimation. It is promising to extending the application of new machine learning algorithms and feature selection methods to improve the accuracy of AGB estimates.

Using UAV LiDAR to Extract Vegetation Parameters of Inner Mongolian Grassland

The accurate estimation of grassland vegetation parameters at a high spatial resolution is important for the sustainable management of grassland areas. Unmanned aerial vehicle (UAV) light detection and ranging (LiDAR) sensors with a single laser beam emission capability can rapidly detect grassland vegetation parameters, such as canopy height, fractional vegetation coverage (FVC) and aboveground biomass (AGB). However, there have been few reports on the ability to detect grassland vegetation parameters based on RIEGL VUX-1 UAV LiDAR (Riegl VUX-1) systems. In this paper, we investigated the ability of Riegl VUX-1 to model the AGB at a 0.1 m pixel resolution in the Hulun Buir grazing platform under different grazing intensities. The LiDAR-derived minimum, mean, and maximum canopy heights and FVC were used to estimate the AGB across the entire grazing platform. The flight height of the LiDAR-derived vegetation parameters was also analyzed. The following results were determined: (1) The Riegl VUX-1-derived AGB was predicted to range from 29 g/m2 to 563 g/m2 under different grazing conditions. (2) The LiDAR-derived maximum canopy height and FVC were the best predictors of grassland AGB (R2 = 0.54, root-mean-square error (RMSE) = 64.76 g/m2). (3) For different UAV flight altitudes from 40 m to 110 m, different flight heights showed no major effect on the derived canopy height. The LiDAR-derived canopy height decreased from 9.19 cm to 8.17 cm, and the standard deviation of the LiDAR-derived canopy height decreased from 3.31 cm to 2.35 cm with increasing UAV flight altitudes. These conclusions could be useful for estimating grasslands in smaller areas and serving as references for other remote sensing datasets for estimating grasslands in larger areas.

Application of a long short-term memory neural network: a burgeoning method of deep learning in forecasting HIV incidence in Guangxi, China

Guangxi, a province in southwestern China, has the second highest reported number of HIV/AIDS cases in China. This study aimed to develop an accurate and effective model to describe the tendency of HIV and to predict its incidence in Guangxi. HIV incidence data of Guangxi from 2005 to 2016 were obtained from the database of the Chinese Center for Disease Control and Prevention. Long short-term memory (LSTM) neural network models, autoregressive integrated moving average (ARIMA) models, generalised regression neural network (GRNN) models and exponential smoothing (ES) were used to fit the incidence data. Data from 2015 and 2016 were used to validate the most suitable models. The model performances were evaluated by evaluating metrics, including mean square error (MSE), root mean square error, mean absolute error and mean absolute percentage error. The LSTM model had the lowest MSE when the N value (time step) was 12. The most appropriate ARIMA models for incidence in 2015 and 2016 were ARIMA (1, 1, 2) (0, 1, 2)₁₂ and ARIMA (2, 1, 0) (1, 1, 2)₁₂, respectively. The accuracy of GRNN and ES models in forecasting HIV incidence in Guangxi was relatively poor. Four performance metrics of the LSTM model were all lower than the ARIMA, GRNN and ES models. The LSTM model was more effective than other time-series models and is important for the monitoring and control of local HIV epidemics.

A Simplified Climate Change Model and Extreme Weather Model Based on a Machine Learning Method

The emergence of climate change (CC) is affecting and changing the development of the natural environment, biological species, and human society. In order to better understand the influence of climate change and provide convincing evidence, the need to quantify the impact of climate change is urgent. In this paper, a climate change model is constructed by using a radial basis function (RBF) neural network. To verify the relevance between climate change and extreme weather (EW), the EW model was built using a support vector machine. In the case study of Canada, its level of climate change was calculated as being 0.2241 (“normal”), and it was found that the factors of CO2 emission, average temperature, and sea surface temperature are significant to Canada’s climate change. In 2025, the climate level of Canada will become “a little bad” based on the prediction results. Then, the Pearson correlation value is calculated as being 0.571, which confirmed the moderate positive correlation between climate change and extreme weather. This paper provides a strong reference for comprehensively understanding the influences brought about by climate change.