The collection of traditional administrative unit-based gross domestic product (GDP) data is time-consuming and laborious, and the data lacks accurate spatial information. Long-term series nighttime light (NTL) data can provide effective spatiotemporal GDP change information, which can be used to analyze economies’ spatial distributions and development trends. In this study, we generated a spatial model of the relationship between NTL indices and GDP parameters, based on NPP-VIIRS-like NTL data for the period 2001 to 2020, conducted a multitemporal and multilevel connectivity analysis of the GDP spatialization data, and constructed a tree structure for horizontal and vertical analysis. Standard deviation ellipses and economic centers of the first-level economic connected components at the provincial and municipal levels were generated, and the economic center distribution range and development direction at the provincial and municipal levels were analyzed. The results show that GDP spatialization data, based on NPP-VIIRS-like NTL data, can intuitively reflect the GDP spatial distribution. In Henan Province, the economic levels of different regions vary, and the economic regions represented by Zhengzhou have developed rapidly, driving surrounding regional economic rapid development. Henan Province’s development trend from single-city economic centers to multicity economic centers is obvious, and the economic center has shifted to the southeast.

Airborne laser scanning (ALS) point cloud has been widely used in various fields, for it can acquire three-dimensional data with a high accuracy on a large scale. However, due to the fact that ALS data are discretely, irregularly distributed and contain noise, it is still a challenge to accurately identify various typical surface objects from 3D point cloud. In recent years, many researchers proved better results in classifying 3D point cloud by using different deep learning methods. However, most of these methods require a large number of training samples and cannot be widely used in complex scenarios. In this paper, we propose an ALS point cloud classification method to integrate an improved fully convolutional network into transfer learning with multi-scale and multi-view deep features. First, the shallow features of the airborne laser scanning point cloud such as height, intensity and change of curvature are extracted to generate feature maps by multi-scale voxel and multi-view projection. Second, these feature maps are fed into the pre-trained DenseNet201 model to derive deep features, which are used as input for a fully convolutional neural network with convolutional and pooling layers. By using this network, the local and global features are integrated to classify the ALS point cloud. Finally, a graph-cuts algorithm considering context information is used to refine the classification results. We tested our method on the semantic 3D labeling dataset of the International Society for Photogrammetry and Remote Sensing (ISPRS). Experimental results show that overall accuracy and the average F1 score obtained by the proposed method is 89.84% and 83.62%, respectively, when only 16,000 points of the original data are used for training.

Image super-resolution (SR) techniques can improve the spatial resolution of remote sensing images to provide more feature details and information, which is important for a wide range of remote sensing applications, including land use/cover classification (LUCC). Convolutional neural networks (CNNs) have achieved impressive results in the field of image SR, but the inherent localization of convolution limits the performance of CNN-based SR models. Therefore, we propose a new method, namely, the dilated Transformer generative adversarial network (DTGAN) for the SR of multispectral remote sensing images. DTGAN combines the local focus of CNNs with the global perspective of Transformers to better capture both local and global features in remote sensing images. We introduce dilated convolutions into the self-attention computation of Transformers to control the network’s focus on different scales of image features. This enhancement improves the network’s ability to reconstruct details at various scales in the images. SR imagery provides richer surface information and reduces ambiguity for the LUCC task, thereby enhancing the accuracy of LUCC. Our work comprises two main stages: remote sensing image SR and LUCC. In the SR stage, we conducted comprehensive experiments on Landsat-8 (L8) and Sentinel-2 (S2) remote sensing datasets. The results indicate that DTGAN generates super-resolution (SR) images with minimal computation. Additionally, it outperforms other methods in terms of the spectral angle mapper (SAM) and learned perceptual image patch similarity (LPIPS) metrics, as well as visual quality. In the LUCC stage, DTGAN was used to generate SR images of areas outside the training samples, and then the SR imagery was used in the LUCC task. The results indicated a significant improvement in the accuracy of LUCC based on SR imagery compared to low-resolution (LR) LUCC maps. Specifically, there were enhancements of 0.130 in precision, 0.178 in recall, and 0.157 in the F1-score.

Net primary productivity (NPP) can effectively represent the growth status of plants. The accurate estimation and spatiotemporal variation analysis of NPP is of great significance for understanding global climate change and carbon cycle. The Carnegie-Ames-Stanford Approach (CASA) model has been extensively utilized for estimating NPP by integrating remote sensing data, climate data, and land cover type data to achieve precise estimations of NPP. However, the traditional CASA model fails to account for the fact that crop types can change over time, leading to inaccurate estimations of NPP in the region. To address this issue, an adaptive temperature stress coefficient for the CASA model (tCASA) is proposed to estimate the NPP of the Central Plains Urban Agglomeration (CUPA) using Landsat time series data spanning from 2002 to 2022. Based on the Theil-Sen Median Estimators, the Mann-Kendall test, and partial correlation analysis, this study delves into the impact of climate and human activities on NPP. The results indicate the following: the Improved tCASA model exhibits a stronger linear correlation with the test dataset, achieving a reduction of 11.11 gC/m2 in the RMSE. The NPP in CUPA demonstrates an increasing trend of 3.0683 gC/m2/year. Across the entire study area, 62.879% of the regions displayed an improvement in NPP, whereas 26.143% showed signs of degradation. Temperature and solar radiation demonstrate a strong positive correlation with NPP, with 73.421% and 72.839% of the region, respectively, positively linked. In contrast, precipitation shows a weaker correlation with NPP, with only 36.848% of the region indicating a positive relationship between precipitation and NPP

Accurate estimation of forest canopy height is crucial for biomass inversion, carbon storage assessment, and forestry management. However, deep learning methods are underutilized compared to machine learning. This paper introduces the convolutional neural network–bidirectional long short-term memory (CNN-BiLSTM) model and proposes a Convolutional Neural network–spatial channel attention–bidirectional long short-term memory (CNN-SCA-BiLSTM) model, incorporating dual attention mechanisms for richer feature extraction. A dataset comprising vegetation indices and canopy height data from forest regions in Luoyang, specifically within the 8–20 m range, is used for a comparative analysis of multiple models, with accuracy evaluated based on the mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R²). The results demonstrate that (1) the CNN-BiLSTM model exhibits strong potential (MAE = 1.6554 m, RMSE = 2.2393 m, R² = 0.9115) and (2) the CNN-SCA-BiLSTM model, while slightly less efficient (<1%), demonstrates improved performance. It reduces the MAE by 0.3047 m, the RMSE by 0.6420 m, and increases the R² value by 0.0495. Furthermore, the model is utilized to generate a canopy height map (MAE = 5.2332 m, RMSE = 7.0426 m) for Henan in the Yellow River Basin for the year 2022. The canopy height is primarily distributed around 5–20 m, approaching the accuracy levels of global maps (MAE = 4.0 m, RMSE = 6.0 m).

High-precision building information extraction is essential in surveying and mapping. Deep learning methods have proven effective in extracting buildings from satellite optical images. This paper introduces a Boundary-Enhanced Semantic Segmentation Model (BE-SegModel) to address the issue of unclear building boundary segmentation in high-resolution satellite images. The model simultaneously extracts building masks and boundary information, ultimately enhancing extraction accuracy. Deep-level heatmaps and feature maps are visualized to analyze the knowledge acquired by the proposed model. The model's performance is evaluated using the xBD, WHU Global, and WHU East Asia Building datasets. Experimental results indicate that, with the inclusion of semantic boundaries, the proposed BE-SegModel outperforms seven mainstream models, including ResNet34, HRNet, Deeplabv3+, CBRNet, FCN, FCN-UNet, and ResNeXt50. In summary, BE-SegModel significantly improves segmentation accuracy, achieving over 6.9% improvement relative to the baseline model.