Currently, there is a wealth of data and expert knowledge available on monitoring agro-meteorological disasters. However, there is still a lack of technical means to organically integrate and analyze heterogeneous data sources in a collaborative manner. This paper proposes a method for monitoring agro-meteorological disasters based on a spatio-temporal knowledge graph. It employs a semantic ontology framework to achieve the organic fusion of multi-source heterogeneous data, including remote sensing data, meteorological data, farmland data, crop information, etc. And it formalizes expert knowledge and computational models into knowledge inference rules, thereby enabling monitoring, early warning, and disaster analysis of agricultural crops within the observed area. The experimental area for this research is the wheat planting region in three counties in Henan Province. The method is tested using simulation monitoring, early warning, and impact calculation of the past two occurrences of dry hot wind disasters. The experimental results demonstrate that the proposed method can provide more specific and accurate warning information and post-disaster analysis results compared to raw records. The statistical results of NDVI decline also validate the correlation between the severity of wheat damage caused by dry hot winds and the intensity and duration of their occurrences. Regarding remote sensing data, this paper proposes a method that directly incorporates remote sensing data into spatio-temporal knowledge inference calculations. By integrating remote sensing data into the regular monitoring process, the advantages of remote sensing data granted by continuous observation are utilized. This approach represents a beneficial attempt to organically integrate remote sensing and meteorological data for monitoring, early warning, and evaluation analysis of agro-meteorological disasters.

With the rapid development of the energy industry and the growth of the global energy demand in recent years, the development of the photovoltaic industry has become increasingly significant. However, the development of the PV industry is constrained by high land costs, and land in central cities and industrial areas is often very expensive and unsuitable for the installation of PV equipment in large areas. With this background knowledge, the key to evaluating the PV potential is by counting the rooftop information of buildings, and an ideal solution for extracting building rooftop information is from remote sensing satellite images using the deep learning method; however, the deep learning method often requires large-scale labeled samples, and the labeling of remote sensing images is often time-consuming and expensive. To reduce the burden of data labeling, models trained on large datasets can be used as pre-trained models (e.g., ImageNet) to provide prior knowledge for training. However, most of the existing pre-trained model parameters are not suitable for direct transfer to remote sensing tasks. In this paper, we design a pseudo-label-guided self-supervised learning (PGSSL) semantic segmentation network structure based on high-resolution remote sensing images to extract building information. The pseudo-label-guided learning method allows the feature results extracted by the pretext task to be more applicable to the target task and ultimately improves segmentation accuracy. Our proposed method achieves better results than current contrastive learning methods in most experiments and uses only about 20–50% of the labeled data to achieve comparable performance with random initialization. In addition, a more accurate statistical method for building density distribution is designed based on the semantic segmentation results. This method addresses the last step of the extraction results oriented to the PV potential assessment, and this paper is validated in Beijing, China, to demonstrate the effectiveness of the proposed method.

Accurate identification of the photovoltaic development status, material, and form of industrial building roofs is essential for delineating roofs available for development and conducting differentiated photovoltaic potential assessments. This study proposes HiFRD-SegFormer, an industrial building roof classification method integrating hierarchical supervision and learnable full-resolution decoding to identify PV-installed roofs, metal pitched roofs, and non-metal flat roofs from high-resolution remote sensing imagery through a single forward pass. A coarse-to-fine architecture combined with coarse-only supervision for ambiguous roofs prevents them from interfering with the classification of the latter two categories, while retaining their reliable non-PV roof information. A learnable full-resolution decoder improves roof-region recovery, boundary delineation, and class discrimination. Experiments on a Shanghai dataset show that HiFRD-SegFormer achieves the best overall performance among several representative segmentation models, with IoUs of 87.53%, 89.73%, and 78.05% for the three classes. Coarse-only supervision balances classification accuracy and roof-area completeness, while the learnable decoder improves Overall IoU by 0.98 pp over SegFormer-B2. Applied to eight districts of Shanghai, the method identifies 79.02 km² of industrial building roofs, comprising 20.31, 38.90, and 19.81 km² of the three classes. These results provide a data basis for PV potential assessment and development planning of industrial building roofs.