Reconstruction of Gap-Free Land Surface Temperature at a 100 m Spatial Resolution from Multidimensional Data: A Case in Wuhan, China.

Land surface temperatures (LST) are vital parameters in land surface-atmosphere interactions. Constrained by technology and atmospheric interferences, LST retrievals from various satellite sensors usually return missing data, thus negatively impacting analyses. Reconstructing missing data is important for acquiring gap-free datasets. However, the current reconstruction methods are limited for maintaining spatial details and high accuracies. We developed a new gap-free algorithm termed the spatial feature-considered random forest regression (SFRFR) model; it builds stable nonlinear relationships to connect the LST with related parameters, including terrain elements, land coverage types, spectral indexes, surface reflectance data, and the spatial feature of the LST, to reconstruct the missing LST data. The SFRFR model reconstructed gap-free LST data retrieved from the Landsat 8 satellite on 27 July 2017 in Wuhan. The results show that the SFRFR model exhibits the best performance according to the various evaluation metrics among the SFRFR, random forest regression and spline interpolation, with a coefficient of determination (R2) reaching 0.96, root-mean-square error (RMSE) of 0.55, and mean absolute error (MAE) of 0.55. Then, we reconstructed gap-free LST data gathered in Wuhan from 2016 to 2021 to analyze urban thermal environment changes and found that 2020 presented the coolest temperatures. The SFRFR model still displayed satisfactory results, with an average R2 of 0.91 and an MAE of 0.63. We further discuss and discover the factors affecting the visual performance of SFRFR and identify the research priority to circumvent these disadvantages. Overall, this study provides a simple, practical method for acquiring gap-free LST data to help us better understand the spatiotemporal LST variation process.

A high-resolution map of soil pH in China made by hybrid modelling of sparse soil data and environmental covariates and its implications for pollution.

The soil's pH is the single most important indicator of the soil's quality, whether for agriculture, pollution control or environmental health and ecosystem functioning. Well documented data on soil pH are sparse for the whole of China - data for only 4700 soil profiles were available from China's Second National Soil Inventory. By combining those data, standardized for the topsoil (0-20 cm), with 17 environmental covariates at a fine resolution (3 arc-second or 90 m) we have predicted the soil's pH at that resolution, that is at more than 109 points. We did so by parallel computing over tiles, each 100 km × 100 km, with two machine learning techniques, namely Random Forest and XGBoost. The predictions for the tiles were then merged into a single map of soil pH for the whole of China. The quality of the predictions were assessed by cross-validation. The root mean squared error (RMSE) was an acceptable 0.71 pH units per point, and Lin's Concordance Correlation Coefficient was 0.84. The hybrid model revealed that climate (mean annual precipitation and mean annual temperature) and soil type were the main factors determining the soil's pH. The pH map showed acid soil mainly in southern and north-eastern China, and alkaline soil dominant in northern and western China. This map can provide a benchmark against which to evaluate the impacts of changes in land use and climate on the soil's pH, and it can guide advisors and agencies who make decisions on remediation and prevention of soil acidification, salinization and pollution by heavy metals, for which we provide examples for cadmium and mercury.

Current and future assessments of soil erosion by water on the Tibetan Plateau based on RUSLE and CMIP5 climate models.

Soil erosion by water is accelerated by a warming climate and negatively impacts water security and ecological conservation. The Tibetan Plateau (TP) has experienced warming at a rate approximately twice that observed globally, and heavy precipitation events lead to an increased risk of erosion. In this study, we assessed current erosion on the TP and predicted potential soil erosion by water in 2050. The study was conducted in three steps. During the first step, we used the Revised Universal Soil Equation (RUSLE), publicly available data, and the most recent earth observations to derive estimates of annual erosion from 2002 to 2016 on the TP at 1-km resolution. During the second step, we used a multiple linear regression (MLR) model and a set of climatic covariates to predict rainfall erosivity on the TP in 2050. The MLR was used to establish the relationship between current rainfall erosivity data and a set of current climatic and other covariates. The coefficients of the MLR were generalised with climate covariates for 2050 derived from the fifth phase of the Coupled Model Intercomparison Project (CMIP5) models to estimate rainfall erosivity in 2050. During the third step, soil erosion by water in 2050 was predicted using rainfall erosivity in 2050 and other erosion factors. The results show that the mean annual soil erosion rate on the TP under current conditions is 2.76tha-1y-1, which is equivalent to an annual soil loss of 559.59×106t. Our 2050 projections suggested that erosion on the TP will increase to 3.17tha-1y-1 and 3.91tha-1y-1 under conditions represented by RCP2.6 and RCP8.5, respectively. The current assessment and future prediction of soil erosion by water on the TP should be valuable for environment protection and soil conservation in this unique region and elsewhere.

[Comparative study on hyperspectral inversion accuracy of soil salt content and electrical conductivity].

The objective of the present article is to ascertain the mechanism of hyperspectral remote sensing monitoring for soil salinization, which is of great importance for improving the accuracy of hyperspectral remote sensing monitoring. Paddy soils in Wensu, Hetian and Baicheng counties of the southern Xinjiang were selected. Hyperspectral data of soils were obtained. Soil salt content (S(t)) an electrical conductivity of 1:5 soil-to-water extracts (EC(1:5)) were determined. Relationships between S(t) and EC(1:5) were studied. Correlations between hyperspectral indices and S(t), and EC(1:5) were analyzed. The inversion accuracy of S(t) using hyperspectral technique was compared with that of EC(1:5). Results showed that: significant (p<0.01) relationships were found between S(t) and EC(1:5) for soils in Wensu and Hetian counties, and correlation coefficients were 0.86 and 0.45, respectively; there was no significant relationship between S(t) and EC(1:5) for soils in Baicheng county. Therefore, the correlations between S(t) and EC(1:5) varied with studied sites. S(t) and EC(1:5) were significantly related with spectral reflectance, first derivative reflectance and continuum-removed reflectance, respectively; but correlation coefficients between S(t) and spectral indices were higher than those between EC(1:5) and spectral indices, which was obvious in some sensitive bands for soil salinization such as 660, 35, 1229, 1414, 1721, 1738, 1772, 2309 nm, and so on. Prediction equations of St and EC(1:5) were established using multivariate linear regression, principal component regression and partial least-squares regression methods, respectively. Coefficients of determination, determination coefficients of prediction, and relative analytical errors of these equations were analyzed. Coefficients of determination and relative analytical errors of equations between S(t) and spectral indices were higher than those of equations between EC(1:5) and spectral indices. Therefore, the responses of high spectral information to St were more sensitive than those of high spectral information to EC(1:5). Accuracy of St predicted from high spectral data was higher than that of EC(1:5) estimated from high spectral data. The results of this study can provide a theoretical basis to improve hyperspectral remote sensing monitoring accuracy of soil salinization.