The collapse of buildings caused by earthquakes can lead to a large loss of life and property. Rapid assessment of building damage with remote sensing image data can support emergency rescues. However, current studies indicate that only a limited sample set can usually be obtained from remote sensing images immediately following an earthquake. Consequently, the difficulty in preparing sufficient training samples constrains the generalization of the model in the identification of earthquake-damaged buildings. To produce a deep learning network model with strong generalization, this study adjusted four Convolutional Neural Network (CNN) models for extracting damaged building information and compared their performance. A sample dataset of damaged buildings was constructed by using multiple disaster images retrieved from the xBD dataset. Using satellite and aerial remote sensing data obtained after the 2008 Wenchuan earthquake, we examined the geographic and data transferability of the deep network model pre-trained on the xBD dataset. The result shows that the network model pre-trained with samples generated from multiple disaster remote sensing images can extract accurately collapsed building information from satellite remote sensing data. Among the adjusted CNN models tested in the study, the adjusted DenseNet121 was the most robust. Transfer learning solved the problem of poor adaptability of the network model to remote sensing images acquired by different platforms and could identify disaster-damaged buildings properly. These results provide a solution to the rapid extraction of earthquake-damaged building information based on a deep learning network model.

Accurate, large-scale classification of tree species -both in forests and for trees outside forests- is essential for monitoring vegetation composition and ecosystem health. Such information strengthens our capacity to detect early-stage biodiversity loss, prioritize conservation interventions, and manage ecosystems more sustainably. Despite increasing availability of high-resolution Earth observation data, operational species-level mapping at continental scales remains limited by heterogeneous sensor characteristics, uneven species distributions, and the difficulty of linking in situ information to multi-sensor imagery.We developed a multi-modal deep learning framework to classify tree species across the Iberian Peninsula. We collected National Forest Inventory (NFI) plot data from mainland Spain paired with Sentinel-1 and Sentinel-2 time series, aerial imagery, aerial lidar, and species presence likelihood derived from bioclimatic variables. Our dataset comprises approx. 40,000 NFI plots with plot-level species counts, while the imagery covers 406 km² and spans ground sampling distances from 20 cm to 10 m. The temporal dimension is captured through a 14-day composite time series, enabling the model to leverage phenological and structural variation throughout the year, while aerial lidar provides fine-grained canopy structure. Our dataset provides fertile ground for exploring multi-modal, multi-scale interactions in high-resolution species modeling.Building on recent advances in foundation models, we implemented a deep neural network (AnySat) fusing these diverse modalities and obtained a scalable, operational high-resolution classifier. The resulting classifier achieved an overall F1 score of 0.70 for the 44 most common species at plot level, demonstrating strong performance across diverse biomes and imaging conditions. Rare, non-dominant species remain a challenge due to the long-tailed distribution of species occurrences. Based on a systematic analysis of modality relevance, we outline strategies for balancing performance with inspiration from long-tailed recognition and semi-supervised learning. Altogether, our dataset and modeling framework advance high-resolution species mapping with remote sensing and illustrate the substantial gains that can be achieved by moving beyond single-modality approaches.

Distinguishing trees on agricultural land from forests is essential for a better understanding of the relationship between forests and human farming activities. However, it is difficult to separate them with remote sensing imagery since they share similar canopy cover, especially on the edge of the amazon rain forest, which has a much-complicated agriculture pattern. Except for annual crops and pasture, there are also lots of agroforestry applications and shifting cultivation, which integrates many tree systems. And those tree systems are not well separated from the forest in the existing land cover map. Recent techniques allow for the mapping of single trees outside of forests, now we take the next step by identifying those diverse tree-involved systems in agricultural land. Here we aim to generate a robust, cost-efficient method to distinguish trees within agricultural land from the forest. We started our exploration from Peruvian Amazon, where the competition for land has increased in the last decades, causing possible adverse effects on livelihoods and ecosystem services. Deep learning models, data sampling, and fine-tuning strategies are tested and optimized with PlanetScope satellite imagery. Our research target is to provide a tool for separating tree systems in farmland from the forest. It can also be used as a base map to explore the dynamic of agriculture transition and its impact on livelihoods and ecosystem services.

Shifting cultivation, in which primary or secondary forest plots are converted into agriculture for one to two years and then left fallow, is often deemed responsible for tropical deforestation. However, the general attribution of deforestation to areas under shifting cultivation is debatable if considering also the component of forest regrowth during the fallow phase, which is an essential part of a mature shifting cultivation system. Yet, little is known about the extent of small-size cropped fields and fallow stages, which are needed to derive information about the temporal development between small-size cropped fields and fallow in shifting cultivation landscapes.The primary objective of our study is to develop a deep learning-based framework to quantify land use intensity in tropical forest nations such as the Democratic Republic of Congo (DRC) using 4.7-m multi-temporal Planet Basemaps from 2015 to 2023. By employing a convolutional neural network image classification model, we first identified the shifting cultivation landscapes. Secondly, utilizing two-phase imagery, we delve into the temporal development of shifting cultivation, determining whether the landscape continues to be characterized by this practice. Thirdly, the shifting cultivation landscapes were segmented into cropped fields, young fallow, old fallow and old-growth forest/primary forest. Lastly, we used a deep learning regression model to quantify the intensity of shifting cultivation within identified areas. This last step adds depth to our analysis, by offering nuanced insights into the varying practices associated with shifting cultivation practices. Our study in DRC offers a detailed spatio-temporal dataset of the dynamics of shifting cultivation serving as a stepping stone to better understand its impacts on forest loss.

Shifting cultivation is often viewed as an agricultural system in decline, driven by policy interventions, agricultural intensification, market integration, land tenure changes, and other socioeconomic drivers. However, mapping its global extent remains challenging because of landscape heterogeneity and the technical barriers that hinder consistent detection. In this study, we combined deep learning with high-resolution satellite imagery to map the extent of shifting cultivation across the pantropics at 1-km resolution. We estimate shifting cultivation covers 211.7 ± 16.2 Mha across 76 countries in 2020, indicating that the system remains prevalent despite reported declines. Globally, 61.4% of shifting cultivation occurs in tropical rainforests, whereas in Africa more than half (55.1%) is found in savanna and open woodland biomes. Mapped areas are frequently located on gentle terrain (below 7° slope). Over 90% of shifting cultivation areas in Asia-Oceania and the Americas are located within 5 km of plantations, compared with 71% in Africa. This global assessment provides a foundation for understanding the persistence, spatial heterogeneity, and contemporary land-use context of shifting cultivation across the pantropics, including its association with agricultural intensification, plantation systems, and socioeconomic development.