Introduction: Leaf area index (LAI) is a critical physiological and biochemical parameter that profoundly affects vegetation growth. Accurately estimating the LAI for winter wheat during jointing stage is particularly important for monitoring wheat growth status and optimizing variable fertilization decisions. Recently, unmanned aerial vehicle (UAV) data and machine/depth learning methods are widely used in crop growth parameter estimation. In traditional methods, vegetation indices (VI) and texture are usually to estimate LAI. Plant Height (PH) unlike them, contains information about the vertical structure of plants, which should be consider.Methods: Taking Xixingdian Township, Cangzhou City, Hebei Province, China as the research area in this paper, and four machine learning algorithms, namely, support vector machine(SVM), back propagation neural network (BPNN), random forest (RF), extreme gradient boosting (XGBoost), and two deep learning algorithms, namely, convolutional neural network (CNN) and long short-term memory neural network (LSTM), were applied to estimate LAI of winter wheat at jointing stage by integrating the spectral and texture features as well as the plant height information from UAV multispectral images. Initially, Digital Surface Model (DSM) and Digital Orthophoto Map (DOM) were generated. Subsequently, the PH, VI and texture features were extracted, and the texture indices (TI) was further constructed. The measured LAI on the ground were collected for the same period and calculated its Pearson correlation coefficient with PH, VI and TI to pick the feature variables with high correlation. The VI, TI, PH and fusion were considered as the independent features, and the sample set partitioning based on joint x-y distance (SPXY) method was used to divide the calibration set and validation set of samples.Results: The ability of different inputs and algorithms to estimate winter wheat LAI were evaluated. The results showed that (1) The addition of PH as a feature variable significantly improved the accuracy of the LAI estimation, indicating that wheat plant height played a vital role as a supplementary parameter for LAI inversion modeling based on traditional indices; (2) The combination of texture features, including normalized difference texture indices (NDTI), difference texture indices (DTI), and ratio texture indices (RTI), substantially improved the correlation between texture features and LAI; Furthermore, multi-feature combinations of VI, TI, and PH exhibited superior capability in estimating LAI for winter wheat; (3) Six regression algorithms have achieved high accuracy in estimating LAI, among which the XGBoost algorithm estimated winter wheat LAI with the highest overall accuracy and best results, achieving the highest R² (R^2 = 0.88), the lowest RMSE (RMSE=0.69), and an RPD greater than 2 (RPD=2.54).Discussion: This study provided compelling evidence that utilizing XGBoost and integrating spectral, texture, and plant height information extracted from UAV data can accurately monitor LAI during the jointing stage of winter wheat. The research results will provide a new perspective for accurate monitoring of crop parameters through remote sensing.

Mastering the regional spatial differences of ecosystem service supply and ecosystem service demand is of great significance to scientifically planning the development and utilization of national land and maintaining healthy development of ecosystems. Based on the relationship analysis of ecosystem service supply and ecosystem service demand, this study explored the regional ecosystem service supply by ecosystem service value based on grid data and constructed an ecosystem service demand evaluation model that integrated the construction land ecosystem service demand equivalent for static aspects and the point of interest (POI) kernel density estimation for dynamic aspects on the basis of land use and POI data. In the end, it put forward a region division method for ecosystem service supply and ecosystem service demand and conducted an empirical analysis of Haidian District, Beijing. The following results were concluded: (1) the ecosystem service value of different grids in Haidian District was between RMB (Chinese monetary unit, Yuan) 0 and RMB 2.4787 million. In terms of spatial distribution, the ecosystem service supply took on an obvious trend of gradual decrease from the northwest to the southeast, with major ecosystem service supply coming from the northwest. (2) The construction land ecosystem service demand equivalent of Haidian District was characterized by a multicenter cluster: the high equivalent area was in the southeast, while the equivalent of the northwest was relatively low. POI kernel density estimation demonstrated cluster distribution, with a high kernel density estimation in the southeast, a lower kernel density estimation in the central part, and the lowest kernel density estimation in the northwest. The ecosystem service demand index also showed cluster distribution: high index in the southeast, low index in the northwest, and prominent sudden changes from the central part to the south. (3) The bivariate local spatial autocorrelation cluster diagram method was used to divide five types of ecosystem service supply and ecosystem service demand, namely non-significant correlation region, high ecosystem service supply and high ecosystem service demand region, high ecosystem service supply and low ecosystem service demand region, low ecosystem service supply and high ecosystem service demand region, low ecosystem service supply and low ecosystem service demand region. Grids with the highest ratio belonged to the non-significant correlation region; the distribution of low ecosystem service supply and high ecosystem service demand region had the greatest concentration, mainly in the southeast; the grids of high ecosystem service supply and low ecosystem service demand region were mainly present in the northwest and in a continuous way; the grids of low ecosystem service supply and low ecosystem service demand region, and high ecosystem service supply and high ecosystem service demand region were extremely few, with sporadic distribution in the central part. The research results could provide a basis for the adjustment and fine management of regional land use structure.

Rural areas are a natural, economic and social complex with multiple functions. Identifying rural multifunction scientifically is the basis for promoting efficient rural spatial planning and sustainable development strategy. In this paper, we calculated and characterized the rural production-living-ecological (PLE) functions at a grid scale of 300 × 300 m in Miyun District by establishing an evaluation index system. Several types of rural functional area were identified with the help of an ISO cluster unsupervised classification tool. Three main results were found as follows. (1) The values of the production, living, ecological functions and multifunction ranged from 0–0.101, 0–0.204, 0.009–0.241 and 0.009–0.302, respectively. Ecological function was dominant in this area. (2) The overall spatial patterns of production and living functions showed the characteristic of being “high in the south and low in the north”, and areas with high values were almost distributed around urban areas and the Miyun Reservoir. While for the ecological function and multifunction, they possessed the opposite characteristics to production and living functions, with high values concentrated in the mountainous areas in the northwest, northeast, east and south of Miyun District. (3) According to the clustering results, rural multifunction of Miyun District was divided into four types: ecological conservation, employment and residence, recreation and potential development, with the area proportions of 44.22%, 17.92%, 20.73% and 17.13%, respectively. Each functional type showed a characteristic of agglomeration. In the future, the study of rural multifunction at micro scales should be paid more attention to better understand the functional differences within the country. This research can provide a decision-making reference for demarcation of rural production-living-ecological space and compilation of spatial planning.

Corn is an important food crop worldwide, and its yield is directly related to Chinese food security. Accurate remote sensing extraction of corn can realize the rational application of land resources, which is of great significance to the sustainable development of modern agriculture. In the field of large-scale crop remote sensing classification, single-period optical remote sensing images often cannot achieve high-precision classification. To improve classification accuracy, multiple time series image combinations have gradually been adopted. However, due to the influence of cloudy and rainy weather, it is often difficult to obtain complete time series optical images. Synthetic aperture radar (SAR) data are imaged by microwaves, which have strong penetrating power and are not affected by clouds. A critical way to solve this problem is to use SAR images to compensate for the lack of optical images and obtain a complete time series image in the corn-growing season. However, SAR images have limited wavelengths and cannot provide important wavelengths, such as visible light bands and near-infrared information. To solve this problem, this study took Zhaodong City, a vital corn-planting base in China, as the research area; took GF-6/GF-3 and Sentinel-1/Sentinel-2 as remote sensing data sources; designed12 classification scenarios; analyzed the best classification period and the best time series combination of corn classification; studied the influence of SAR images on the classification results of time series images; and compared the classification differences between GF-6/GF-3 and Sentinel-1/Sentinel-2. The results show that the classification accuracy of time series combinations is much higher than that of single-period images. The polarization characteristics of SAR images can improve the classification accuracy with time series images. The classification accuracy of GF series images from China is obviously higher than that of Sentinel series images. The research performed in this paper can provide a reference for agricultural classification by using remote sensing data.

The scientific selection of photovoltaic (PV) sites is essential for achieving sustainable development of renewable energy and ensuring regional ecological security. In western China, extensive land resources coexist with a fragile ecological environment. To this end, we propose a PV siting framework based on policy restrictions and construction suitability. This paper evaluated the PV construction suitability index (CSI) from four dimensions of topography, climate, location, and ecology and proposed typical “PV+” models. Then, Qilian County was selected as a case study. The results showed the following: (1) In Qilian, 59.97% (8333.18 km²) of the area is unsuitable for development due to policy restrictions, leaving 40.03% (5563.02 km²) available for PV construction. (2) The most suitable areas are approximately in the western and southern areas, where there is a lot in common with the reported PV sites under construction. (3) Three distinct PV development models are proposed according to policy guidelines and local circumstances, including the PV + pastoralism model, PV + mine rehabilitation model, and PV + hydropower model. The results can be used to determine the suitable areas for solar PV farms and the appropriate development model, as well as promote the sustainable development of renewable energy.