Glacial melting in the Tibetan Plateau affects the water resources of millions of people. This study finds that—partly owing to changes in atmospheric circulations and precipitation patterns—the most intensive glacier shrinkage is in the Himalayan region, whereas glacial retreat in the Pamir Plateau region is less apparent.

Different glacier status with atmospheric circulations in Tibetan Plateau and surroundings

Deep learning in environmental remote sensing: Achievements and challenges

[1] Changes in regional groundwater storage in North China were estimated from the Gravity Recovery and Climate Experiment (GRACE) satellites data and ground-based measurements collected from 2003 to 2010. The study area (∼370,000 km2) included the Beijing and Tianjin municipality, the Hebei and Shanxi province, which is one of the largest irrigation areas in the world and is subjected to intensive groundwater-based irrigation. Groundwater depletion in North China was estimated by removing the simulated soil moisture changes from the GRACE-derived terrestrial water storage changes. The rate of groundwater depletion in North China based on GRACE was 2.2 ± 0.3 cm/yr from 2003 to 2010, which is equivalent to a volume of 8.3 ± 1.1 km3/yr. The groundwater depletion rate estimated from monitoring well stations during the same time period was between 2.0 and 2.8 cm/yr, which is consistent with the GRACE-based result. However, the estimated groundwater depletion rate in shallow plain aquifers according to the Groundwater Bulletin of China Northern Plains (GBCNP) for the same time period was only approximately 2.5 km3/yr. The difference in groundwater depletion rates estimated from GRACE and GBCNP data indicates the important contribution of groundwater depletion from deep aquifers in the plain and piedmont regions of North China.

Evaluation of groundwater depletion in North China using the Gravity Recovery and Climate Experiment (GRACE) data and ground-based measurements (EI)

In situ soil moisture data from more than 200 stations located in Africa, Australia, Europe and the United States are used to determine the reliability of three soil moisture products, one analysis from the ECMWF (European Centre for Medium-Range Weather Forecasts) numerical weather prediction system (SM-DAS-2) and two remotely sensed soil moisture products, namely ASCAT (Advanced scatterometer) and SMOS (Soil Moisture Ocean Salinity). SM-DAS-2 is produced offline at ECMWF and relies on an advanced surface data assimilation system (Extended Kalman Filter) used to optimally combine conventional observations with satellite measurements. ASCAT remotely sensed surface soil moisture is provided in near real time by EUMETSAT. At ECMWF, ASCAT is used for soil moisture analyses in SM-DAS-2, also. Finally the SMOS remotely sensed soil moisture data level two product developed at CESBIO is used. Evaluation of the times series as well as of the anomaly values, shows good performances of the three products to capture surface soil moisture annual cycle and short term variability. Correlations with in situ data are very satisfactory over most of the investigated sites located in contrasted biomes and climate conditions with averaged values of 0.70 for SM-DAS-2, 0.53 for ASCAT and 0.54 for SMOS. Although radio frequency interference disturbs the natural microwave emission of the Earth observed by SMOS in several parts of the world, hence the soil moisture retrieval, performances of SMOS over Australia are very encouraging.

Evaluation of remotely sensed and modelled soil moisture products using global ground-based in situ observations

Random forests (RF) is a supervised machine learning algorithm, which has recently started to gain prominence in water resources applications. However, existing applications are generally restricted to the implementation of Breiman’s original algorithm for regression and classification problems, while numerous developments could be also useful in solving diverse practical problems in the water sector. Here we popularize RF and their variants for the practicing water scientist, and discuss related concepts and techniques, which have received less attention from the water science and hydrologic communities. In doing so, we review RF applications in water resources, highlight the potential of the original algorithm and its variants, and assess the degree of RF exploitation in a diverse range of applications. Relevant implementations of random forests, as well as related concepts and techniques in the R programming language, are also covered.

https://www.mdpi.com/2073-4441/11/5/910/pdf

A Brief Review of Random Forests for Water Scientists and Practitioners and Their Recent History in Water Resources

Timely and accurate estimation of the area and distribution of crops is vital for food security. Optical remote sensing has been a key technique for acquiring crop area and conditions on regional to global scales, but great challenges arise due to frequent cloudy days in southern China. This makes optical remote sensing images usually unavailable. Synthetic aperture radar (SAR) could bridge this gap since it is less affected by clouds. The recent availability of Sentinel-1A (S1A) SAR imagery with a 12-day revisit period at a high spatial resolution of about 10 m makes it possible to fully utilize phenological information to improve early crop classification. In deep learning methods, one-dimensional convolutional neural networks (1D CNNs), long short-term memory recurrent neural networks (LSTM RNNs), and gated recurrent unit RNNs (GRU RNNs) have been shown to efficiently extract temporal features for classification tasks. However, due to the complexity of training, these three deep learning methods have been less used in early crop classification. In this work, we attempted to combine them with an incremental classification method to avoid the need for training optimal architectures and hyper-parameters for data from each time series. First, we trained 1D CNNs, LSTM RNNs, and GRU RNNs based on the full images’ time series to attain three classifiers with optimal architectures and hyper-parameters. Then, starting at the first time point, we performed an incremental classification process to train each classifier using all of the previous data, and obtained a classification network with all parameter values (including the hyper-parameters) at each time point. Finally, test accuracies of each time point were assessed for each crop type to determine the optimal time series length. A case study was conducted in Suixi and Leizhou counties of Zhanjiang City, China. To verify the effectiveness of this method, we also implemented the classic random forest (RF) approach. The results were as follows: (i) 1D CNNs achieved the highest Kappa coefficient (0.942) of the four classifiers, and the highest value (0.934) in the GRU RNNs time series was attained earlier than with other classifiers; (ii) all three deep learning methods and the RF achieved F measures above 0.900 before the end of growth seasons of banana, eucalyptus, second-season paddy rice, and sugarcane; while, the 1D CNN classifier was the only one that could obtain an F-measure above 0.900 for pineapple before harvest. All results indicated the effectiveness of the solution combining the deep learning models with the incremental classification approach for early crop classification. This method is expected to provide new perspectives for early mapping of croplands in cloudy areas.

Evaluation of Three Deep Learning Models for Early Crop Classification Using Sentinel-1A Imagery Time Series—A Case Study in Zhanjiang, China

Precipitation is an important controlling parameter for land surface processes, and is crucial to ecological, environmental, and hydrological modeling. In this study, we propose a spatial downscaling approach based on precipitation–land surface characteristics. Land surface temperature features were introduced as new variables in addition to the Normalized Difference Vegetation Index (NDVI) and Digital Elevation Model (DEM) to improve the spatial downscaling algorithm. Two machine learning algorithms, Random Forests (RF) and support vector machine (SVM), were implemented to downscale the yearly Tropical Rainfall Measuring Mission 3B43 V7 (TRMM 3B43 V7) precipitation data from 25 km to 1 km over the Tibetan Plateau area, and the downscaled results were validated on the basis of observations from meteorological stations and comparisons with previous downscaling algorithms. According to the validation results, the RF and SVM-based models produced higher accuracy than the exponential regression (ER) model and multiple linear regression (MLR) model. The downscaled results also had higher accuracy than the original TRMM 3B43 V7 dataset. Moreover, models including land surface temperature variables (LSTs) performed better than those without LSTs, indicating the significance of considering precipitation–land surface temperature when downscaling TRMM 3B43 V7 precipitation data. The RF model with only NDVI and DEM produced much worse accuracy than the SVM model with the same variables. This indicates that the Random Forests algorithm is more sensitive to LSTs than the SVM when downscaling yearly TRMM 3B43 V7 precipitation data over Tibetan Plateau. Moreover, the precipitation–LSTs relationship is more instantaneous, making it more likely to downscale precipitation at a monthly or weekly temporal scale.

A Spatial Downscaling Algorithm for Satellite-Based Precipitation over the Tibetan Plateau Based on NDVI, DEM, and Land Surface Temperature

Environmental monitoring of Earth from space has provided invaluable information for understanding land–atmosphere water and energy exchanges. However, the use of satellite-based precipitation observations in hydrologic and environmental applications is often limited by their coarse spatial resolutions. In this study, we propose a downscaling approach based on precipitation–land surface characteristics. Daytime land surface temperature, nighttime land surface temperature, and day–night land surface temperature differences were introduced as variables in addition to the Normalized Difference Vegetation Index (NDVI), the Digital Elevation Model (DEM), and geolocation (longitude, latitude). Four machine learning regression algorithms, the classification and regression tree (CART), the k-nearest neighbors (k-NN), the support vector machine (SVM), and random forests (RF), were implemented to downscale monthly TRMM 3B43 V7 precipitation data from 25 km to 1 km over North China for the purpose of comparison of algorithm performance. The downscaled results were validated based on observations from meteorological stations and were also compared to a previous downscaling algorithm. According to the validation results, the RF-based model produced the results with the highest accuracy. It was followed by SVM, CART, and k-NN, but the accuracy of the downscaled results using SVM relied greatly on residual correction. The downscaled results were well correlated with the observations during the year, but the accuracies were relatively lower in July to September. Downscaling errors increase as monthly total precipitation increases, but the RF model was less affected by this proportional effect between errors and observation compared with the other algorithms. The variable importances of the land surface temperature (LST) feature variables were higher than those of NDVI, which indicates the significance of considering the precipitation–land surface temperature relationship when downscaling TRMM 3B43 V7 precipitation data.

A Comparison of Different Regression Algorithms for Downscaling Monthly Satellite-Based Precipitation over North China

Although numerous satellite-based soil moisture (SM) products can provide spatiotemporally continuous worldwide datasets, they can hardly be employed in characterizing fine-grained regional land surface processes, owing to their coarse spatial resolution. In this study, we proposed a machine-learning-based method to enhance SM spatial accuracy and improve the availability of SM data. Four machine learning algorithms, including classification and regression trees (CART), K-nearest neighbors (KNN), Bayesian (BAYE), and random forests (RF), were implemented to downscale the monthly European Space Agency Climate Change Initiative (ESA CCI) SM product from 25-km to 1-km spatial resolution. During the regression, the land surface temperature (including daytime temperature, nighttime temperature, and diurnal fluctuation temperature), normalized difference vegetation index, surface reflections (red band, blue band, NIR band and MIR band), and digital elevation model were taken as explanatory variables to produce fine spatial resolution SM. We chose Northeast China as the study area and acquired corresponding SM data from 2003 to 2012 in unfrozen seasons. The reconstructed SM datasets were validated against in-situ measurements. The results showed that the RF-downscaled results had superior matching performance to both ESA CCI SM and in-situ measurements, and can positively respond to precipitation variation. Additionally, the RF was less affected by parameters, which revealed its robustness. Both CART and KNN ranked second. Compared to KNN, CART had a relatively close correlation with the validation data, but KNN showed preferable precision. Moreover, BAYE ranked last with significantly abnormal regression values.

Comparison of Different Machine Learning Approaches for Monthly Satellite-Based Soil Moisture Downscaling over Northeast China

Mapping urban areas at global and regional scales is an urgent and crucial task for detecting urbanization and human activities throughout the world and is useful for discerning the influence of urban expansion upon the ecosystem and the surrounding environment. DMSP-OLS stable nighttime lights have provided an effective way to monitor human activities on a global scale. Threshold-based algorithms have been widely used for extracting urban areas and estimating urban expansion, but the accuracy can decrease because of the empirical and subjective selection of threshold values. This paper proposes an approach for extracting urban areas with the integration of DMSP-OLS stable nighttime lights and MODIS data utilizing training sample datasets selected from DMSP-OLS and MODIS NDVI based on several simple strategies. Four classification algorithms were implemented for comparison: the classification and regression tree (CART), k-nearest-neighbors (k-NN), support vector machine (SVM), and random forests (RF). A case study was carried out on the eastern part of China, covering 99 cities and 1,027,700 km(2). The classification results were validated using an independent land cover dataset, and then compared with an existing contextual classification method. The results showed that the new method can achieve results with comparable accuracies, and is easier to implement and less sensitive to the initial thresholds than the contextual method. Among the four classifiers implemented, RF achieved the most stable results and the highest average Kappa. Meanwhile CART produced highly overestimated results compared to the other three classifiers. Although k-NN and SVM tended to produce similar accuracy, less-bright areas around the urban cores seemed to be ignored when using SVM, which led to the underestimation of urban areas. Furthermore, quantity assessment showed that the results produced by k-NN, SVM, and RFs exhibited better agreement in larger cities and low consistency in small cities.

Wenlong Jing

Papers

Evaluation of Three Deep Learning Models for Early Crop Classification Using Sentinel-1A Imagery Time Series—A Case Study in Zhanjiang, China

A Spatial Downscaling Algorithm for Satellite-Based Precipitation over the Tibetan Plateau Based on NDVI, DEM, and Land Surface Temperature

A Comparison of Different Regression Algorithms for Downscaling Monthly Satellite-Based Precipitation over North China

Comparison of Different Machine Learning Approaches for Monthly Satellite-Based Soil Moisture Downscaling over Northeast China

Mapping Urban Areas with Integration of DMSP/OLS Nighttime Light and MODIS Data Using Machine Learning Techniques