Leaf area index (LAI) is a fundamental indicator of crop growth status, timely and non-destructive estimation of LAI is of significant importance for precision agriculture. In this study, a multi-rotor UAV platform equipped with CMOS image sensors was used to capture maize canopy information, simultaneously, a total of 264 ground‐measured LAI data were collected during a 2-year field experiment. Linear regression (LR), backpropagation neural network (BPNN), and random forest (RF) algorithms were used to establish LAI estimation models, and their performances were evaluated through 500 repetitions of random sub-sampling, training, and testing. The results showed that RGB-based VIs derived from UAV digital images were strongly related to LAI, and the grain-filling stage (GS) of maize was identified as the optimal period for LAI estimation. The RF model performed best at both whole period and individual growth stages, with the highest R²(0.71–0.88) and the lowest RMSE (0.12–0.25) on test datasets, followed by the BPNN model and LR models. In addition, a smaller 5–95% interval range of R²and RMSE was observed in the RF model, which indicated that the RF model has good generalization ability and is able to produce reliable estimation results.

Digital soil mapping has emerged as a new method to describe the spatial distribution of soils economically and efficiently. In this study, a lightweight soil organic matter (SOM) mapping method based on a deep residual network, which we call LSM-ResNet, is proposed to make accurate predictions with background covariates. ResNet not only integrates spatial background information around the observed environmental covariates, but also reduces problems such as information loss, which undermines the integrity of information and reduces prediction uncertainty. To train the model, rectified linear units, mean squared error, and adaptive momentum estimation were used as the activation function, loss/cost function, and optimizer, respectively. The method was tested with Landsat5, the meteorological data from WorldClim, and the 1602 sampling points set from Xinxiang, China. The performance of the proposed LSM-ResNet was compared to a traditional machine learning algorithm, the random forest (RF) algorithm, and a training set (80%) and a test set (20%) were created to test both models. The results showed that the LSM-ResNet (RMSE = 6.40, R² = 0.51) model outperformed the RF model in both the roots mean square error (RMSE) and coefficient of determination (R²), and the training accuracy was significantly improved compared to RF (RMSE = 6.81, R² = 0.46). The trained LSM-ResNet model was used for SOM prediction in Xinxiang, a district of plain terrain in China. The prediction maps can be deemed an accurate reflection of the spatial variability of the SOM distribution.

Semantic segmentation is a key technology for remote sensing image analysis widely used in land cover classification, natural disaster monitoring, and other fields. Unlike traditional image segmentation, there are various targets in remote sensing images, with a large feature difference between the targets. As a result, segmentation is more difficult, and the existing models retain low accuracy and inaccurate edge segmentation when used in remote sensing images. This paper proposes a multi-attention-based semantic segmentation network for remote sensing images in order to address these problems. Specifically, we choose UNet as the baseline model, using a coordinate attention-based residual network in the encoder to improve the extraction capability of the backbone network for fine-grained features. We use a content-aware reorganization module in the decoder to replace the traditional upsampling operator to improve the network information extraction capability, and, in addition, we propose a fused attention module for feature map fusion after upsampling, aiming to solve the multi-scale problem. We evaluate our proposed model on the WHDLD dataset and our self-labeled Lu County dataset. The model achieved an mIOU of 63.27% and 72.83%, and an mPA of 74.86% and 84.72%, respectively. Through comparison and confusion matrix analysis, our model outperformed commonly used benchmark models on both datasets.

The microwave backscattering model is one of the most effective tools for surface soil moisture (SSM) inversion, which has strong theoretical support, but the inverse problem is difficult to solve. Advance in artificial intelligence offers possibilities to learn complex nonlinear relationships in a data-driven way, but it lacks physical mechanism. To combine the advantages of model-driven and data-driven methods, an SSM inversion approach that couples the AIEM-Oh model with Deep neural networks (DNNs) was proposed in this study. DNNs with different inputs were trained with a large number of simulation data generated from the AIEM-Oh model, thus embedding physical mechanisms in the data-driven scheme. Two field experiments at different scales were carried out to evaluate the performances of the proposed approach over bare surfaces. The effects of polarization modes and prior knowledge of surface roughness on SSM inversion were explored, and the accuracy of the approach was compared with the existing methods. The results suggest that satisfactory accuracy was obtained by the proposed approach, the RMSE between the measured and estimated values of SSM was 0.03-0.04 cm3·cm-3 with prior knowledge of soil roughness, and the RMSE was 0.08-0.10 cm3·cm-3 without the prior soil roughness information. VV polarization was more sensitive to SSM over bare surfaces than VH polarization. Moreover, the approach showed stable performance in different experimental regions. The results demonstrate the capability and reliability of the coupled approach for SSM inversion over bare surfaces.

Soil C, N contents and C:N stoichiometry are important indicators of soil quality, the variation characteristics of which have great significance for soil carbon-nitrogen cycle and sustainable utilization. Based on 597 observations along with soil profiles of 0–20cm depth in the 1980s and the 2010s, the temporal and spatial variations of soil C, N contents and C:N stoichiometry in the major grain-producing region of the North China Plain were illustrated. Results showed that there were significant changes in soil C, N contents over time, with increasing rates of 60.47% and 50%, respectively. The changes of C, N contents resulting in a general improvement of C:N stoichiometry. There was a significant decline in nugget effects of soil C, N contents from the 1980s to 2010s, the spatial autocorrelation of soil nutrients showed an increasing trend, and the effect of random variation was reduced. C:N stoichiometry was higher in Huixian City and Weihui City, and lower in Yanjin County, an apparent decline was observed in the spatial difference of soil C:N stoichiometry from the 1980s to 2010s. Soil C, N contents and C:N stoichiometry differed among soil types, agricultural land-use types, and topography in space. The temperature, precipitation, and fertilization structure were considered as the main factors that induce the temporal variations. These findings indicated that the soil nutrient elements in the farmland ecosystems changed in varying degrees in both time and space scales, and the variation was influenced by soil types, land-use types, topography, meteorological factors, and fertilization structure.

With the rapid development of the social economy in China, numerous Chinese cities are facing high levels of particulate matter (PM) pollution problems. In this study, high-resolution ZY-3 images and GIS techniques were used to establish the emission inventory of total suspended particle (TSP), particulate matter 10 (PM₁₀) and particulate matter 2.5 (PM_2.5) from fugitive dust sources in May 2016, and a spatial grid of 3 km × 3 km resolution was established to demonstrate the spatial distribution of PM emission. Results showed that the total emissions of TSP, PM₁₀ and PM_2.5 in Zhengzhou city were 237.5 kt·a⁻¹, 103.7 kt·a⁻¹ and 22.4 kt·a⁻¹, respectively. Construction dust source was the main fugitive dust emission source in Zhengzhou city—the TSP, PM₁₀ and PM_2.5 emission of which account for 76.42%, 89.68% and 88.39%, respectively, of the total emission, followed by road dust source and soil dust source. PM emission was higher in Zhongyuan, Huiji, Jinshui and Zhengdong New District, while Zhongmou, Xingyang, Dengfeng and other remote areas had low PM emissions. Compared to other Chinese cities or regions, the PM emission from the construction dust source was at a high level in Zhengzhou city, while the PM emissions from the soil dust source and road dust source were at moderate levels.