Nowadays, rapid advancements in remote sensing technology has led to widespread recognition of its potential to improve the efficiency and reliability of crop inspection and monitoring. The objectives of this project are 1. to create a database of annual remote sensing data for economic crops from satellite imagery; 2. to study the cultivation patterns of economic crops based on annual changes in reflectance values; and 3. to study the relationship between spectral signatures and growth characteristics obtained from field surveys. From the remote sensing data from Sentinel 2, we calculated vegetation indices such as the Normalized Difference Vegetation Index (NDVI), the Green Normalized Difference Vegetation Index (GNDVI) and the Normalized Difference Infrared Index (NDII) to study their correlation with the crop growth parameters of five economic crops in Thailand, namely sugarcane, cassava, pineapple, oil palm, and pararubber. The results show that the spectral reflectance of each crop changes all year round and is synchronized with growth data such as height, canopy width, stem size, and leaf chlorophyll content. Therefore, the remote sensing data have potential for the growth and health monitoring of the five economic tropical crops. The satellite imagery from a specific month can be used to create crop growth assessment models including height, canopy width, stem size, and leaf chlorophyll content. In addition, the effectiveness of the model depends on the type of vegetation index used.

Autonomous exploration is an essential characteristic for Unmanned Aerial Vehicle (UAV) swarms operating in complex and unfamiliar surroundings. This work presents Swarm-RRT*, a unique Guided-Rapidly exploring Random Tree (Guided-RRT*) search algorithm for UAV swarms that enables fast and resilient exploration. The suggested technique combines the swarming paradigm with the conventional RRT approach to improve path planning, coverage, and obstacle avoidance in dynamic situations. A guiding system based on information acquisition and geographical distribution is presented to coordinate the UAV swarm, assuring thorough investigation while reducing duplicate pathways. The Guided-RRT technique dynamically modifies search tree development using the heuristic function and Voronoï principle to guide the exploration while avoiding exploration within the Voronoï region. Extensive simulation tests show that the suggested technique surpasses traditional RRT-based approaches in time complexity, exploration efficiency, coverage rate, and computing cost. This study adds to advances in remote sensing through drone technology by proposing a scalable UAV swarm guided by the RRT* solution for survey, mapping, search and rescue, and environmental monitoring.

The lunar surface represents a platform for investigating planetary evolution, technological innovation, and potential extraterrestrial resource utilization. This study presents a high-resolution geospatial distribution mapping of the transition metals iron (Fe), titanium (Ti), and chromium (Cr) within Dryden Crater, utilizing advanced hyperspectral remote sensing methodologies.
Our research integrates hyperspectral data from NASA's Moon Mineralogy Mapper (M3) imaging spectrometer, deployed on the Chandrayaan-1 mission, in conjunction with the lunar digital elevation model (SLDEM2015) topographical dataset from the Lunar Orbiter Laser Altimeter (LOLA) and SELenological and Engineering Explorer (SELENE) Kaguya Terrain camera.
Employing sophisticated spectral indexing techniques and RGB compositional analysis, we conducted a comprehensive quantitative assessment of transition metal distributions. The resultant geochemical map delineates precise spatial boundaries and concentration gradients of Fe, Ti, and Cr within the lunar crater's geological context.
Our interdisciplinary approach demonstrates the efficacy of integrated international scientific collaboration through open data policy, leveraging advanced spectroscopic techniques to unravel the complex geochemical landscape of lunar surface environments. This research contributes to our understanding of planetary geological processes and potential extraterrestrial resource exploitation strategies.

The Moon continues to engage scientific interest as a critical platform for technological innovation and potential extraterrestrial resource exploration. This research presents a comprehensive mineralogical characterization of the Dryden crater located in the South Pole–Aitken basin (SPA) leveraging state-of-the-art remote sensing and spectral mapping technologies.
Our methodology synthesizes hyperspectral data from NASA's Moon Mineralogy Mapper (M3), integrated with topographical datasets from the Lunar Orbiter Laser Altimeter (LOLA) and SELenological and Engineering Explorer (SELENE) Kaguya digital elevation model (SLDEM2015). By employing sophisticated MoonIndex spectral indices and RGB compositional mapping, we conducted a detailed surface composition investigation.
The resulting mineral map reveals distributions of pyroxene and anorthosite, precisely delineating their spatial boundaries. This detailed mineralogical assessment provides critical insights into the crater's geological evolution, offering valuable contextual information for future lunar exploration strategies.
This work supports strategic mission planning, identifies potential resource locations, and paves the way for future robotic and human lunar exploration, expanding our collective knowledge of planetary scientific frontiers.

Extreme drought periods have severely affected forests in Central Europe in the last few years. As a result, extended wilting, defoliation and die-out events have severely impacted several tree species. Within the framework of the ForstEO research project, we evaluated the capability of deep learning approaches to identify tree crown damage in selected areas of Bavaria, Germany. We used 20 cm aerial imagery from different years: 2019 (June and August), 2020, 2021 and 2023. We provide an analysis of the accuracy of wall-to-wall image segmentation and give insights into the feasibility of generating models that are transferable to other datasets. We evaluated the following scenarios: 1) two classes: background and damaged trees; 2) three classes: background, damaged deciduous trees and damaged coniferous trees; and 3) four classes: similar classes as in 2, but with the damaged conifer classsplit into pine and other conifers. We trained several U-Net variants for semantic segmentation using image patches and masks obtained from four different datasets, and applied the generalized models to classify a test area for the studied years. The highest mean interclass IoU for the models attained 0.82 for the 2-class, 0.73 for the 3-class and 0.69 for the 4-class cases. Among the three evaluated forest categories, detection rates varied significantly depending on the dataset. As a trend, damaged deciduous trees exhibited the highest detection values, whereas conifers demonstrated the lowest. When the best model was applied to unseen data (June 2019), IoU achieved a best mean of 0.78 for the 2-class, 0.69 for the 3-class and 0.59 for the 4-class cases. The general models showed robust performance on all datasets. However, the transferability of these models needs to be further investigated.

Surface heat transfer is a continuous process that describes the dynamical equilibrium between the magmatic system and the host rock. In volcanic systems, part of the energy transfer from magma drives fluid convection and increases ground temperatures. Total heat transfer occurs by the combination of three processes: conductive, convective and radiative heat flow. Any of these processes has a different load in the volcanic system, and their detection needs different methodologies and approaches. Steaming ground and fumaroles show the convective heat flow reaching the ground surface; mild thermal anomalies reflect conductive heat transfer within the ground; and multi-spectral instruments can detect the heat flow radiating from the ground surface. The continuous monitoring network deployed on the Island of Vulcano (Italy) showed transient variations in the heat flow released by the active cone, always related to increasing seismic activity and ground deformations. Some contact sensors monitor the time variations of high-temperature fumaroles; other sensors monitor time variations of heat flux in the mild thermal zone associated with diffuse degassing. The resulting long-term time series tracked several unrests (e.g. Diliberto 2021, Federico et al., 2023).

We present results from the integration of AI techniques and different monitoring procedures, measuring the following: a) ground temperature by contact sensors on selected sites; b) fumarole extension; c) thermal and environmental indices from satellite imagery. In particular, we employed a Semi-Supervised Generative Adversarial Network (SGAN) model to classify different levels of volcanic states (background activity, transient degassing and updated degassing level) automatically. The model leverages direct temperature measurements from contact sensors (deployed by the ground-based network on La Fossa cone), land surface temperature anomalies (from MODIS), the Normalized Thermal Index (from VIIRS) and the environmental indices NDVI, NDWI, NDMI (from Landsat 8). Preliminary results show how the SGAN's accuracy is over 0.89 for almost all the considered time intervals.

Nowadays, in the autonomous flight missions of UAVs (unmanned aerial vehicles) , precise observation and prompt decision-making are of paramount importance. Accurate segmentation and detection of transmission towers and powerlines from a UAV’s perspective is practically for ensuring safe and efficient path guidance for these UAVs. However, the complexity of the scene often makes it difficult to capture powerlines, as they are extremely thin and can easily blend into the background, posing a significant challenge in their detection. To solve this problem, we utilize a large foundation model known as the Segment Anything Model (SAM), which is designed to enhance the capacity for localizing and accurately segmenting powerlines within confusing scenes. Based on SAM, we propose a finetuning decoder to transfer the generalized class-agnostic knowledge of SAM to class-aware downstream task. Extensive experiments on multiple benchmark datasets (TTPLA、PLID、PLDU、PLDM) demostrate the efficiency of our proposed method. The comparison results with previous methods show that our method achieves the current state-of-the-art performance on transmission towers and powerlines segmentation task.

Lima Metropolitana, the world’s second most arid megacity, has grown from ~577,000 inhabitants in 1945 to over 11 million by 2024. This rapid expansion has drastically reduced agricultural land and poses challenges for food security, poverty reduction, and sustainability.

This study integrates historical aerial photographs (1944–1984) with Landsat-based remote sensing (1984–2023) to map and quantify land transformations. Using Google Earth Engine, we preprocessed Landsat imagery (4–9) for cloud removal and spectral analysis. A Random Forest classifier, trained on annotated points for each LULC class, employed 150 decision trees, a minimum leaf population of 1, a bag fraction of 0.6, and a fixed seed. The model achieved ~95.3% accuracy, with most classes showing high precision (>0.93) and recall (>0.90).

Over eight decades, Lima lost 84% of its agricultural land (42,370 ha to 6,751 ha) while urban areas surged from 1,950 ha to 65,938 ha. Nearly half of this expansion took place on hillsides and barren lands, often inhabited by vulnerable communities. This decline in local agriculture increased reliance on external food sources, exacerbating insecurity and social inequalities. Between 2007 and 2017, the lowest socioeconomic strata grew from 344,472 to over 1.1 million (3.3-fold).

In response, community-led initiatives like “Ollas Comunes” (Community Soup Kitchens) have emerged as critical coping strategies, serving over 240,000 individuals daily, primarily from low-income households. These grassroots efforts underscore the urgent need for integrated urban planning that prioritizes social equity, food security, and environmental resilience.

By detailing the scale and implications of Lima’s land-use transformations, this research highlights the necessity of conserving remaining farmlands, promoting urban agriculture, and incorporating inclusive, community-driven solutions. Such measures are essential for forging a more equitable, sustainable, and food-secure future amidst ongoing urban growth and climatic constraints.

Remote sensing often faces challenges such as motion blur, overexposure, and limited dynamic range, particularly in extreme lighting and high-speed scenarios. To overcome these limitations, this study introduces a novel framework that integrates event cameras, infrared imaging, and deep learning techniques for robust and high-quality image fusion.

Event cameras capture rapid light intensity changes with high dynamic range and microsecond-level temporal resolution, making them ideal for preserving motion details and texture in challenging environments. Infrared imaging complements this by providing thermal data unaffected by lighting variations. By combining these two modalities, the framework leverages their complementary strengths for improved scene understanding.

The proposed framework employs deep learning to perform three key tasks: reconstructing visible textures from event data, deblurring infrared images guided by event-based motion cues, and fusing the features of both modalities. A bi-level optimization process reduces redundancy while preserving essential information, resulting in clearer and more detailed fused images.

Experiments on synthetic and real-world datasets demonstrate the framework's ability to outperform state-of-the-art methods, particularly in dynamic and low-visibility conditions. This work highlights the transformative potential of integrating event cameras and infrared imaging with deep learning, offering a powerful solution for complex remote sensing scenarios.

Monitoring rainfall is essential to understanding hydrological processes, managing water resources, and mitigating drought and flood risks. Many regions, particularly in developing countries, have sparse rain-gauge networks, limiting the spatial coverage and resulting in inaccurate rainfall estimates. By combining remote sensing data with rain-gauge measurements, rainfall estimates can be improved, and spatial coverage can be enhanced. Remote sensing techniques provide a valuable resource for supplementing and enhancing rainfall monitoring in such areas. This study leverages Global Precipitation Measurement (GPM) satellite data to enhance rainfall estimation in White Nile State, Sudan, where only two rain-gauge stations are operational; the state's total area is 39.600 Km². GPM data, well known for its high temporal and spatial resolution, offer a promising alternative to mitigate the limitations of sparse ground-based networks. The study integrates GPM satellite data with ground-based measurements through statistical and geostatistical techniques, and validation, to improve rainfall accuracy. The results indicate that GPM data effectively complement rain-gauge observations, capturing spatial rainfall patterns and extreme events more accurately. The findings underscore the potential of remote sensing to provide reliable rainfall information in data-scarce regions, contributing to better water resource management and disaster risk reduction strategies.