Li Wang

Reliable estimation and mapping of soil salinity content (SSC) offer crucial information for sustainable agricultural development and food safety. Ensemble learning utilizing unmanned aerial vehicle (UAV) imagery has proven to be effective in estimating soil properties. Nevertheless, due to the high dimensionality of data and the variability in performance among different base learners within ensemble learning, effective methods that can identify sensitive features and optimize base learners remain to be explored. Furthermore, the mechanism by which soil auxiliary information, such as soil organic matter (SOM) and pH, influences the accuracy of SSC estimation is not yet fully understood. In this study, we proposed a novel ensemble learning framework, named feature-optimized and performance-weighted ensemble learning (FOPW-EL), for estimating SSC using UAV imagery and soil auxiliary information. This framework incorporated the hybrid embedded feature selection (HEFS) to extract sensitive features and the CRITIC (Criteria Importance Through Intercriteria Correlation)–Entropy combined weighting (CECW) to identify the optimal base learners. Our results demonstrate that the FOPW-EL model substantially outperformed all other models, with average validation metrics of the coefficient of determination ( R ² ) of 0.752, ratio of prediction to deviation (RPD) of 1.744, and linear correlation consistency coefficient (LCCC) of 0.792. Additionally, the FOPW-EL model exhibited low prediction uncertainty, with the global uncertainty index consistently below 0.39. We identified SOM, salinity index (SI2), normalized difference salinity red edge index (NDSIREG), and pH as the most sensitive feature variables. The feature importance assessment indicates that spectral indices played a key role in SSC modeling, accounting for 58.94% of the contribution. The analysis of partial dependence plots revealed a strong positive correlation between SI2 and SSC, with a correlation coefficient of 0.76. In contrast, SOM and pH values showed significant negative correlations with SSC, with correlation coefficients of −0.42 and −0.22, respectively. These findings indicate that this proposed method holds considerable promise for providing accurate, cost-effective, and efficient SSC estimation, which could greatly aid in soil quality monitoring.

Accurately predicting arsenic (As) concentration in farmland soil on a large scale is essential for effectively preventing and managing soil pollution in agricultural areas, thereby safeguarding food security. Multispectral imaging presents a cost-effective and efficient method for monitoring As concentration across extensive farmland regions. Nevertheless, the underlying process and mechanisms determining the relationship between As concentration in farmland soil and spectral data remain uncertain. The primary aim of this study was to evaluate whether employing a hierarchical strategy (based on soil organic matter (SOM) and pH) results in more accurate prediction of As concentration in farmland soil than those employing nonhierarchical (global) models. Our results show that with respect to global models, the best prediction of As concentration was achieved using the convolutional neural network (CNN) model (validated ratio of the model performance to the interquartile distance (RPIQ) = 2.50), followed by the Cubist model (validated RPIQ = 2.19) and the extreme learning machine (ELM) model (validated RPIQ = 2.10). After SOM-based hierarchization, the Cubist model exhibited the highest prediction accuracy (validated coefficient of determination (R²) = 0.73), representing a 0.02 improvement in the R² compared with the that of global CNN model. The clay minerals ratio (CMR) was identified as the most important variable for predicting As concentration. Notably, the identification of high As concentration in the central old town areas underscores the importance of early soil contamination risk warnings on arable lands. These findings indicate that SOM-hierarchical machine learning models could serve as an effective approach to addressing the influence of soil environmental complications on spectral prediction of As concentration in farmland soil. By implementing this proposed method, soil environmental monitoring efforts can be significantly improved.

Land use/cover change (LUCC) accompanied by climate change and human activities will have unpredictable impacts on watershed ecosystems. However, the extent to which these land use changes affect the spatial and temporal distribution of ecosystem services (ESs) in different regions remains unclear. The impact of LUCC on ESs in the Qingjiang Watershed (QJW), an ecologically sensitive area, and LUCC’s role in future ESs under different land use scenarios are crucial to promoting ecological conservation and land use management. This paper assessed water yield (WY), soil conservation (SC), carbon storage (CS) and habitat quality (HQ) using the InVEST model, and their responses to LUCC in the QJW from 1990 to 2018 using the geodetector and multiscale geographically weighted regression. We predicted land use patterns using the Logistic–CA–Markov model and their effects on ESs in 2034 under business as usual (BAU), ecological land protection (ELP), arable land protection (ALP) and ecological economic construction (EEC) scenarios. From 1990 to 2018, the area of cropland and woodland decreased by 28.3 and 138.17 km², respectively, while the built-up land increased by 96.65 km². The WY increased by 18.92%, while the SC, CS and HQ decreased by 26.94%, 1.05% and 0.4%, respectively. The increase in the arable land area led to a increase in WY, and the decrease in forest land and the increase in construction land led to a decrease in SC, CS and HQ. In addition to being influenced by land use patterns, WY and SC were influenced mainly by meteorological and topographical factors, respectively. In 2034, there was an obvious spatial growth conflict between cropland and construction land, especially in the area centered on Lichuan, Enshi and Yidu counties. Under four scenarios, WY and SC were ranked ALP > BAU > EEC > ELP, while CS and HQ were ranked ELP > EEC > BAU > ALP. Considering the sustainable eco-socio-economic development of the QJW, the EEC scenario can be chosen as a future development plan. These results can indicate how to rationally improve the supply of watershed ESs through land resource allocation, promoting sustainable regional development in mountainous watershed areas.

Soil organic matter (SOM) is vital for assessing the quality of arable land. A fast and reliable estimation of SOM is important to predict the soil carbon stock in cropland. In this study, we aimed to explore the potential of combining multitemporal Sentinel-2A imagery and random forest (RF) to improve the accuracy of SOM estimates in the plough layer for cultivated land at a regional scale. The field data of SOM content were utilized along with multitemporal Sentinel-2A images acquired over three years during the bare soil period to develop spectral indices. The best bands and spectral indices were selected as prediction variables by using the RF algorithm. Partial least squares (PLS), geographically weighted regression (GWR), and RF were employed to calibrate spectral indices for the SOM content, and the optimal calibration model was used for the mapping of the SOM content in arable land at a regional scale. The results showed the following. (1) The multitemporal image estimation model outperformed the single-temporal image estimation model. The estimation model that utilized the optimal bands and spectral indices as prediction variables usually had better accuracy than the models based on full spectral data. (2) For the SOM content estimates, the performance was better with RF than with PLS and GWR in almost all cases. (3) The most accurate SOM estimation in the case area was achieved by using multitemporal images from 2018 and the RF calibration model based on the optimal bands and spectral indices as prediction variables, with R²_val (coefficient of determination of the validation data set) = 0.67, RMSE_val (root mean square error of the validation dataset) = 2.05, and RPIQ_val (ratio of performance to interquartile range of the validation dataset) = 3.36. (4) The estimated SOM content in the plough layer for cultivated land throughout the study area ranged from 16.17 to 36.98 g kg⁻¹ and exhibited an increasing trend from north to south. In the current study, we developed a framework that combines multitemporal remote sensing imagery and RF for the SOM estimation, which can improve the accuracy of quantitative SOM estimations, provide a dynamic, rapid, and low-cost technique for understanding soil fertility, and offer an early warning of changes in soil quality.

Rapid urbanization and industrialization have brought about regional prosperity and pressure on the ecological environment, and the disorder of development has led to competition among the production-living-ecology functions. How to build livable cities, optimize the spatial layout of land, and promote the coordinated development of the production-living-ecology functions in various regions has become an important issue in the sustainable development and utilization of land space. In order to study the spatiotemporal conflict and coordination of the production-living-ecology functions with respect to the dramatic developments associated with the 21st century, this study took Hubei Province, which is the top-ranking economic region in China in recent years, as the study area and adopted the global entropy value method, triangle model, and coupled evaluation model to delineate an index system to measure the degree of conflict and coordination of the production-living-ecology functions in Hubei Province from 2000 to 2020, and also delineate zoning management based on statistical yearbook data. The results showed the following: (1) With respect to the time scale, the indices of the production-living-ecology functions in Hubei Province increased year by year, and the degree of coordination also increased yearly, from the stage of disorder with certain conflict to the stage of coordination with a high level of coupling. (2) On the spatial scale, the development of production-living-ecology functions in Hubei Province was unbalanced, which may be related to the overall development strategy of “two circles and one belt” in Hubei Province, with the eastern part of the province having a higher degree of coordination of the production-living-ecology functions and the western part having a lower degree of coordination. (3) Among the production-living-ecology functions, the ecological function of Hubei Province as a whole exhibited minimal change and maintained stable development, while the living and production functions underwent considerable development, indicating that Hubei Province has protected the orderly development of the ecological environment in the process of urbanization and new industrialization. (4) According to the development and coordination of the production-living-ecology functions in each region of Hubei Province, four development management zones were created: high-quality development zone, secondary development zone, balanced development zone, and development potential zone. Finally, policy suggestions are given for each zone.

With the increasing aging of the world’s population, research on the equitable allocation of elderly care facilities has received increasing attention, but measuring the accessibility of community care facilities (CCFs) in rural areas has received little attention. In this study, which covered 7985 CCFs in 223,877 villages, we measured the accessibility of CCFs in rural areas of Hubei Province by using the nearest distance method. Based on the accessibility calculation, the spatial disparities and agglomeration characteristics of spatial accessibility were analyzed, and the correlated variables related to the accessibility were analyzed from both natural environment and socioeconomic aspects by employing a geographically weighted regression (GWR) model. Our results show that 87% of villages have a distance cost of less than 7121 m and 81% of townships have a distance cost of less than 5114 m; good spatial accessibility is present in the eastern and central regions, while poor spatial accessibility is shown in a small number of areas in the west. The results from the clustering analysis show that the hot spot areas are mainly clustered in the western mountainous areas and that the cold spot areas are mainly clustered around Wuhan city. We also observed that area, elevation, population aged 65 and above, and number of villages are significantly correlated with accessibility. The results of this study can be used to provide a reference for configuration optimization and layout planning of elderly care facilities in rural areas.

Controlling soil erosion is beneficial to the conservation of soil resources and ecological restoration. Understanding the spatial distribution characteristics of soil erosion helps find the key areas for soil control projects and optimal scale for investing in a soil and water conservation project at the lowest cost. This study aims to answer the question of how the spatial distribution of soil erosion in Hubei Province changed between 2000 and 2020. Moreover, how do the effects of natural factors and human activities on soil erosion vary over the years? What are the differences in landscape pattern characteristics and the spatial cluster of soil erosion at multiple administrative scales? We simulated the spatial distribution of soil erosion in Hubei province from 2000 to 2020 by the Chinese Soil Loss Equation model at three administrative scales. We investigated the relationship between soil erosion and driving factors by Geodector. We explored the landscape pattern and hotspots of land at different levels of soil erosion by Fragstat and hotspot analysis. The results show that: (1) The average soil erosion rate decreased from 2000 to 2020. Soil erosion is severe in the mountainous areas of western Hubei province, while it is less severe in the central plains. (2) Land-cover type, precipitation, and normalized difference vegetation index are the most influencing factors of soil erosion in 2000–2010, 2015, and 2020, respectively. (3) The aggregation index values at the town scale are higher than those at the city and county scales, while the fractal dimension index values at the town scale are lower, which indicates that soil erosion projects are most efficient when the project unit is ‘town’. (4) At the town scale, if the hotspot area (6.84% of the total area) is treated as the protection target, it can reduce 50.42% of the total soil erosion of Hubei province. Hotspots of soil erosion overlap with high erosion zones, mainly in the northwestern, northeastern, and southwestern parts of Hubei province in 2000, while the hotspots in northwestern Hubei disappear in 2020. In conclusion, land managers in Hubei should optimize the land-use structure, soil and water conservation in slope land, and eco-engineering controls at the town scale.

Forest land is the carrier for growing forests. It is of great significance to evaluate the forest land quality scientifically and delineate forestland protection zones reasonably for realizing better forest land management, promoting ecological civilization construction, and coping with global climate change. In this study, taking Hefeng County, Hubei Province, a subtropical humid evergreen broad-leaved forest region in China, as the study area, 14 indicators were selected from four dimensions—climatic conditions, terrain, soil conditions, and socioeconomics—to construct a forest land quality evaluation index system. Based on the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) model, we introduced the Particle Swarm Optimization (PSO) algorithm to design the evaluation model to evaluate the forest land quality and analyze the distribution of forest land quality in Hefeng. Further, we used the Local Indicator of Spatial Association (LISA) to explore the spatial distribution of forest land quality and delineate the forest land protection zones. The results showed the following: (1) the overall quality of forest land was high, with some variability between regions. The range of Forest Land Quality Index (FLQI) in Hefeng was 0.4091–0.8601, with a mean value of 0.6337. The forest land quality grades were mainly first and second grade, with the higher-grade forest land mainly distributed in the central and southeastern low mountain regions of Zouma, Wuli, and Yanzi. The lower-grade forest land was mainly distributed in the northwestern middle and high mountain regions of Zhongying, Taiping, and Rongmei. (2) The global spatial autocorrelation index of forest land quality in Hefeng County was 0.7562, indicating that the forest land quality in the county had a strong spatial similarity. The spatial distribution of similarity types high-high (HH) and low-low (LL) was more clustered, while the spatial distribution of dissimilarity types high-low (HL) and low-high (LH) was generally dispersed. (3) Based on the LISA of forest land quality, forest land protection zones were divided into three types: key protection zones (KPZs), active protection zones (APZs), and general protection zones (GPZs). The forest land protection zoning basically coincided with the forest land quality. Combining the characteristics of self-correlated types in different forestland protection zones, corresponding management and protection measures were proposed. This showed that the PSO-TOPSIS model can be effectively used for forest land quality evaluation. At the same time, the spatial attributes of forest land were incorporated into the development of forest land protection zoning scheme, which expands the method of forest land protection zoning, and can provide a scientific basis and methodological reference for the reasonable formulation of forest land use planning in Hefeng County, while also serving as a reference for similar regions and countries.

Understanding the spatial pattern of soil chemical properties (SCPs) together with topological factors and soil management practices is essential for land management. This study examines the spatial changes in soil chemical properties and their impact on China’s subtropical mountainous areas. In 2007 and 2017, 290 and 200 soil samples, respectively, were collected in Hefeng County, a mountainous county in central China. We used descriptive statistics and geostatistical methods, including ANOVA, semivariance, Moran’s I, and fractal dimensions, to analyze the characteristics and spatial autocorrelation changes in soil organic matter (OM), available phosphorus (AP), available potassium (AK), and pH value from 2007 to 2017. We explored the relationship between each SCP and the relationship between SCPs with topographic parameters, soil texture, and cropping systems. The results show that the mean value of soil OM, AP, AK, and pH in Hefeng increased from 2007 to 2017. The spatial variation and spatial dependency of each SCP in 2007, excluding AP and AK in 2007, were higher than in 2017. The soil in areas with high topographic relief, profile curvature, and planform curvature had less AP, AK, and pH. Soil at higher elevation had lower OM (r = −0.197, p < 0.01; r = −0.334, p < 0.01) and AP (r = −0.043, p < 0.05; r = −0.121, p < 0.05) and higher AK (r = −0.305, p < 0.01; r = 0.408, p < 0.01) in 2007 and 2017. Soil OM and AK in 2007 were significantly (p < 0.05) correlated with soil texture (p < 0.05). In contrast, oil AP and soil pH in 2007 and all SCPs in 2017 were poorly correlated with soil texture. The cropping systems played an important role in affecting all SCPs in 2007 (p < 0.01), while they only significantly affected AK in 2017 (p < 0.05). Our findings demonstrate that both topological factors, that is, the changes in cropping management and the changes in acid rain, impact soil chemical properties. The local government should place more focus on reducing soil acid amounts, soil AP content, and soil erosion by improving water conservancy facilities.

Constructing a scientific and quantitative quality-assessment model for farmland is important for understanding farmland quality, and can provide a theoretical basis and technical support for formulating rational and effective management policies and realizing the sustainable use of farmland resources. To more accurately reflect the systematic, complex, and differential characteristics of farmland quality, this study aimed to explore an intelligent farmland quality-assessment method that avoids the subjectivity of determining indicator weights while improving assessment accuracy. Taking Xiangzhou in Hubei Province, China, as the study area, 14 indicators were selected from four dimensions—terrain, soil conditions, socioeconomics, and ecological environment—to build a comprehensive assessment index system for farmland quality applicable to the region. A total of 1590 representative samples in Xiangzhou were selected, of which 1110 were used as training samples, 320 as test samples, and 160 as validation samples. Three models of entropy weight (EW), backpropagation neural network (BPNN), and random forest (RF) were selected for training, and the assessment results of farmland quality were output through simulations to compare their assessment accuracy and analyze the distribution pattern of farmland quality grades in Xiangzhou in 2018. The results showed the following: (1) The RF model for farmland quality assessment required fewer parameters, and could simulate the complex relationships between indicators more accurately and analyze each indicator’s contribution to farmland quality scientifically. (2) In terms of the average quality index of farmland, RF > BPNN > EW. The spatial patterns of the quality index from RF and BPNN were similar, and both were significantly different from EW. (3) In terms of the assessment results and precision characterization indicators, the assessment results of RF were more in line with realities of natural and socioeconomic development, with higher applicability and reliability. (4) Compared to BPNN and EW, RF had a higher data mining ability and training accuracy, and its assessment result was the best. The coefficient of determination (R²) was 0.8145, the mean absolute error (MAE) was 0.009, and the mean squared error (MSE) was 0.012. (5) The overall quality of farmland in Xiangzhou was higher, with a larger area of second- and third-grade farmland, accounting for 54.63%, and the grade basically conformed to the trend of positive distribution, showing an obvious pattern of geographical distribution, with overall high performance in the north-central part and low in the south. The distribution of farmland quality grades also varied widely among regions. This showed that RF was more suitable for the quality assessment of farmland with complex nonlinear characteristics. This study enriches and improves the index system and methodological research of farmland quality assessment at the county scale, and provides a basis for achieving a threefold production pattern of farmland quantity, quality, and ecology in Xiangzhou, while also serving as a reference for similar regions and countries.