A comprehensive interpretation of remote sensing images involves not only remote sensing object recognition but also the recognition of spatial relations between objects. Especially in the case of different objects with the same spectrum, the spatial relationship can help interpret remote sensing objects more accurately. Compared with traditional remote sensing object recognition methods, deep learning has the advantages of high accuracy and strong generalizability regarding scene classification and semantic segmentation. However, it is difficult to simultaneously recognize remote sensing objects and their spatial relationship from end-to-end only relying on present deep learning networks. To address this problem, we propose a multi-scale remote sensing image interpretation network, called the MSRIN. The architecture of the MSRIN is a parallel deep neural network based on a fully convolutional network (FCN), a U-Net, and a long short-term memory network (LSTM). The MSRIN recognizes remote sensing objects and their spatial relationship through three processes. First, the MSRIN defines a multi-scale remote sensing image caption strategy and simultaneously segments the same image using the FCN and U-Net on different spatial scales so that a two-scale hierarchy is formed. The output of the FCN and U-Net are masked to obtain the location and boundaries of remote sensing objects. Second, using an attention-based LSTM, the remote sensing image captions include the remote sensing objects (nouns) and their spatial relationships described with natural language. Finally, we designed a remote sensing object recognition and correction mechanism to build the relationship between nouns in captions and object mask graphs using an attention weight matrix to transfer the spatial relationship from captions to objects mask graphs. In other words, the MSRIN simultaneously realizes the semantic segmentation of the remote sensing objects and their spatial relationship identification end-to-end. Experimental results demonstrated that the matching rate between samples and the mask graph increased by 67.37 percentage points, and the matching rate between nouns and the mask graph increased by 41.78 percentage points compared to before correction. The proposed MSRIN has achieved remarkable results.

Landscape alterations and ecosystem services (ES) are crucial elements that affect the socio-ecological development of ecologically fragile regions. To provide scientific support for the land-use planning and regional ecological restoration to achieve sustainable development goals (SDGs) in the Loess Plateau from 1992 to 2015, this study proposes an integrated assessment framework for assessing the supply – demand match and equilibrium of ES combining potential relationships between landscape alterations, ES, and sustainable development at the county and regional scales. Results show that more than 85% of local counties have a supply – demand mismatch in terms of ecosystem services. Supply – demand distributions for provisioning and supporting services were relatively balanced compared to cultural services, which were imbalanced. Although the overall supply – demand relationship is relatively balanced because of the significant influence of ecological restoration, it shows an increasing trend toward imbalance as human – land conflict is prominent in some regions. SDGs emphasize on specific ES information such as ecosystem conservation, sustainable agriculture, and urban construction. Furtherly, positive impacts from landscape dynamics can improve the supply capacity of the ES and contribute to regional sustainability.

Temperature forecasting is a crucial part of climate change research. It can provide a valuable reference, as well as practical significance, for understanding the macroscopic evolutionary processes of regional temperature and for promoting sustainable development. This study presents a new integrated model, called the Variational Mode Decomposition-Autoregressive Integrated Moving Average (VMD-ARIMA) model, which reduces the required data input and improves the accuracy of predictions, based on the deficiencies of data dependence and the complicated mechanisms associated with current temperature forecasting. In this model, the variational mode decomposition (VMD) was used for mining the trend features and detailed features contained in a time series, as well as denoising. Moreover, the corresponding autoregressive integrated moving average (ARIMA) models were derived to reflect the different features of the components. The final forecasted values were then obtained using VMD reconstruction. The annual temperature time series from the Wuhan Meteorological Station were investigated using the VMD-ARIMA model, ARIMA model, and Grey Model (1, 1) based on three statistical performance metrics (mean relative error, mean absolute error, and root mean square error). The results indicate that the VMD-ARIMA model can effectively enhance the accuracy of temperature forecasting.

The layout and configuration of urban infrastructure are essential for the orderly operation and healthy development of cities. With the promotion and popularization of new energy vehicles, the modeling and prediction of charging pile usage and allocation have garnered significant attention from governments and enterprises. Short-term demand forecasting for charging piles is crucial for their efficient operation. However, existing prediction models lack a discussion on the appropriate time window, resulting in limitations in station-level predictions. Recognizing the temporal nature of charging pile occupancy, this paper proposes a novel stacked-LSTM model called attention-SLSTM that integrates an attention mechanism to predict the charging demand of electric vehicles at the station level over the next few hours. To evaluate its performance, this paper compares it with several methods. The experimental results demonstrate that the attention-SLSTM model outperforms both LSTM and stacked-LSTM models. Deep learning methods generally outperform traditional time series forecasting methods. In the test set, MAE is 1.6860, RMSE is 2.5040, and MAPE is 9.7680%. Compared to the stacked-LSTM model, MAE and RMSE are reduced by 4.7%and 5%, respectively; while MAPE value decreases by 1.3%, making it superior to LSTM overall. Furthermore, subsequent experiments compare prediction performance among different charging stations, which confirms that the attention-SLSTM model exhibits excellent predictive capabilities within a six-step (2 h) window.