Comparison of spectral and spatial-based approaches for mapping the local variation of soil moisture in a semi-arid mountainous area

Deep learning and data fusion to estimate surface soil moisture from multi-sensor satellite images

We propose a new architecture based on a fully connected feed-forward Artificial Neural Network (ANN) model to estimate surface soil moisture from satellite images on a large alluvial fan of the Kosi River in the Himalayan Foreland. We have extracted nine different features from Sentinel-1 (dual-polarised radar backscatter), Sentinel-2 (red and near-infrared bands), and Shuttle Radar Topographic Mission (digital elevation model) satellite products by leveraging the linear data fusion and graphical indicators. We performed a feature importance analysis by using the regression ensemble tree approach and also feature sensitivity to evaluate the impact of each feature on the response variable. For training and assessing the model performance, we conducted two field campaigns on the Kosi Fan in December 11-19, 2019 and March 01-06, 2022. We used a calibrated TDR probe to measure surface soil moisture at 224 different locations distributed throughout the fan surface. We used input features to train, validate, and test the performance of the feed-forward ANN model in a 60:10:30 ratio, respectively. We compared the performance of ANN model with ten different machine learning algorithms [i.e., Generalised Regression Neural Network (GRNN), Radial Basis Network (RBN), Exact RBN (ERBN), Gaussian Process Regression (GPR), Support Vector Regression (SVR), Random Forest (RF), Boosting Ensemble Learning (Boosting EL), Recurrent Neural Network (RNN), Binary Decision Tree (BDT), and Automated Machine Learning (AutoML)]. We observed that the ANN model accurately predicts the soil moisture and outperforms all the benchmark algorithms with correlation coefficient (R = 0.80), Root Mean Square Error (RMSE = 0.040 [Formula: see text]), and bias = 0.004 [Formula: see text]. Finally, for an unbiased and robust conclusion, we performed spatial distribution analysis by creating thirty different sets of training-validation-testing datasets. We observed that the performance remains consistent in all thirty scenarios. The outcomes of this study will foster new and existing applications of soil moisture.

Heterogeneous catalysis mediated by light, electricity and enzyme via machine learning: Paradigms, applications and prospects

Energy crisis and environmental pollution have become the bottleneck of human sustainable development. Therefore, there is an urgent need to develop new catalysts for energy production and environmental remediation. Due to the high cost caused by blind screening and limited valuable computing resources, the traditional experimental methods and theoretical calculations are difficult to meet with the requirements. In the past decades, computer science has made great progress, especially in the field of machine learning (ML). As a new research paradigm, ML greatly accelerates the theoretical calculation methods represented by first principal calculation and molecular dynamics, and establish the physical picture of heterogeneous catalytic processes for energy and environment. This review firstly summarized the general research paradigms of ML in the discovery of catalysts. Then, the latest progresses of ML in light-, electricity- and enzyme-mediated heterogeneous catalysis were reviewed from the perspective of catalytic performance, operating conditions and reaction mechanism. The general guidelines of ML for heterogeneous catalysis were proposed. Finally, the existing problems and future development trend of ML in heterogeneous catalysis mediated by light, electricity and enzyme were summarized. We highly expect that this review will facilitate the interaction between ML and heterogeneous catalysis, and illuminate the development prospect of heterogeneous catalysis.

A Data-Driven Method for the Temporal Estimation of Soil Water Potential and Its Application for Shallow Landslides Prediction

Soil water potential is a key factor to study water dynamics in soil and for estimating the occurrence of natural hazards, as landslides. This parameter can be measured in field or estimated through physically-based models, limited by the availability of effective input soil properties and preliminary calibrations. Data-driven models, based on machine learning techniques, could overcome these gaps. The aim of this paper is then to develop an innovative machine learning methodology to assess soil water potential trends and to implement them in models to predict shallow landslides. Monitoring data since 2012 from test-sites slopes in Oltrepò Pavese (northern Italy) were used to build the models. Within the tested techniques, Random Forest models allowed an outstanding reconstruction of measured soil water potential temporal trends. Each model is sensitive to meteorological and hydrological characteristics according to soil depths and features. Reliability of the proposed models was confirmed by correct estimation of days when shallow landslides were triggered in the study areas in December 2020, after implementing the modeled trends on a slope stability model, and by the correct choice of physically-based rainfall thresholds. These results confirm the potential application of the developed methodology to estimate hydrological scenarios that could be used for decision-making purposes.

Characterizing soil salinity at multiple depth using electromagnetic induction and remote sensing data with random forests: A case study in Tarim River Basin of southern Xinjiang, China

Tarim River Basin is experiencing heavy soil degeneration in a long term because of the extreme natural conditions, added with improper human activities such as reclamation and rejected field repeatedly, which hindered the soil health. One of the mainly form is soil salinization. Spatial distribution and variation of soil salinity is essential both for agricultural resource management and local economic development. However, knowledge of the spatial distribution of soil salinization in this region has not been updated since 1980s while land use and climate have undergone major changed. Electromagnetic induction (EMI) has been successfully used to directly measurement the spatial distribution of targeting soil property at field- scale, and apparent electrical conductivity (ECa, mS m^-1) has become a surrogate of soil salinity (EC, dS m^-1) studied by many researchers at local scale. However, the effectiveness of this equipment has not been verified in the typical soil salinization areas in southern Xinjiang, especially on a large scale. This study was aimed to test the performance of ECa jointed with Random Forest (RF) for soil salinity regional-scale mapping at a typical arid area, taking Tarim River Basin as an example. The result showed that ECa together with environmental derivative variables and with RF were suited for regional-scale soil salinity mapping. Predicted accuracy of EC was higher at surface (0-20 cm, R² = 0.65, RMSE = 5.59) and deeper soil depth (60-80 cm, R² = 0.63, RMSE = 2.00, and 80-100 cm, R² = 0.61, RMSE = 1.73), lower at transitional zone (20-40 cm, R² = 0.55, RMSE = 2.66, and 40-60 cm, R² = 0.51, RMSE = 2.49). When ECa is involved in modeling, the prediction accuracy of multiple depths of EC is improved by 13.33%-61.54%, of which the most obvious depths are 60-80 cm and 0-20 cm. The results of variable importance show that SoilGrids were also favored the power EC model. Hence, we strongly recommended to joint EMI reads with remote sensing imagery for soil salinity monitoring at large scale in southern Xinjiang. These EC and ECa map can provide a data source for environmental modeling, a benchmark against which to evaluate and monitor water and salt dynamics, and a guide for the design of future soil surveys.

Comparison of Soil Total Nitrogen Content Prediction Models Based on Vis-NIR Spectroscopy

Visible-near-infrared spectrum (Vis-NIR) spectroscopy technology is one of the most important methods for non-destructive and rapid detection of soil total nitrogen (STN) content. In order to find a practical way to build STN content prediction model, three conventional machine learning methods and one deep learning approach are investigated and their predictive performances are compared and analyzed by using a public dataset called LUCAS Soil (19,019 samples). The three conventional machine learning methods include ordinary least square estimation (OLSE), random forest (RF), and extreme learning machine (ELM), while for the deep learning method, three different structures of convolutional neural network (CNN) incorporated Inception module are constructed and investigated. In order to clarify effectiveness of different pre-treatments on predicting STN content, the three conventional machine learning methods are combined with four pre-processing approaches (including baseline correction, smoothing, dimensional reduction, and feature selection) are investigated, compared, and analyzed. The results indicate that the baseline-corrected and smoothed ELM model reaches practical precision (coefficient of determination (R²) = 0.89, root mean square error of prediction (RMSEP) = 1.60 g/kg, and residual prediction deviation (RPD) = 2.34). While among three different structured CNN models, the one with more 1 × 1 convolutions preforms better (R² = 0.93; RMSEP = 0.95 g/kg; and RPD = 3.85 in optimal case). In addition, in order to evaluate the influence of data set characteristics on the model, the LUCAS data set was divided into different data subsets according to dataset size, organic carbon (OC) content and countries, and the results show that the deep learning method is more effective and practical than conventional machine learning methods and, on the premise of enough data samples, it can be used to build a robust STN content prediction model with high accuracy for the same type of soil with similar agricultural treatment.

Using Apparent Electrical Conductivity as Indicator for Investigating Potential Spatial Variation of Soil Salinity across Seven Oases along Tarim River in Southern Xinjiang, China

Soil salinization is a major soil health issue globally. Over the past 40 years, extreme weather and increasing human activity have profoundly changed the spatial distribution of land use and water resources across seven oases in southern Xinjiang, China. However, knowledge of the spatial distribution of soil salinization in this region has not been updated since a land survey in the 1970s to 1980s (the harmonized world soil database, HWSD) due to scarce observational data. Now, given the uncertainty raised by near future climate change, it is important to develop quick, reliable and accurate estimates of soil salinity at larger scales for a better manage strategy to the local fragile ecosystem that with limited land and water resources. This study collected electromagnetic induction (EMI) readings near surface soil to update on the spatial distribution and changes of water and salt in the region and to map apparent electrical conductivity (ECa, mS·m−1), in four coil configurations: vertical dipole in 1.50 m (ECav01) and 0.75 m (ECav05), so as the horizontal dipole in 0.75 m (ECah01) and 0.37 m (ECah05), then all the ECa coil configurations were modeled with random forest algorithm. The validation results showed an R2 range of 0.77–0.84 and an RMSE range of 115.17–142.76 mS·m−1. The validation accuracy of deep ECa dipole (ECah01, ECav05, and ECav01) was greater than that of shallow ECa (ECah05), as the former integrated a thicker portion of the subsurface. The range of EC spatial variability that can be explained by ECa is 0.19–0.36 (farmland, mean value is 0.28), grassland is 0.16–0.49 (shrub/grassland, mean value is 0.34), and bare land is 0.28–0.70 (bare land, mean value is 0.56). Among them, ECav01 has the best predictive ability. As the depth increased, the influence of soil-related variables decreased, and the contribution of climate-related variables increased. The main factor affecting ECa variation was climate-related variables, followed by vegetation-related variables and soil-related variables. Scatter plot show ECa was significantly correlated with ECe_HWSD_030 (0–30 cm, r = 0.482, p < 0.01) and ECe_HWSD_30100 (30–100 cm, r = 0.556, p < 0.01). The predicted spatial ECa maps were similar to the ECe values from HWSD, but also implies that the distribution of soil water and salt has undergone tremendous changes since 1980s. The study demonstrates that EMI data provide a reliable and cost-effective tool for obtaining high-resolution soil maps that can be used for better land evaluation and soil improvement at larger scales.