Geo-Sensing

This dataset integrates multi-source geophysical precursor data from seismically active regions, and constructs standardized data containing spatial and temporal parameters and anomalous signal intensities through denoising, normalization, and anomaly correction, aiming to support the detection of seismic precursor anomalies, the study of mechanisms, and the development of early-warning models, and to provide a high-reliability data base for seismic anomaly detection and risk assessment.

The dataset provided in this study contains variables related to solar power generation, including solar irradiance, temperature, wind speed, and humidity in Riyadh. The data was collected using NASA satellite imagery and various ground stations over a period of time. This dataset is crucial for improving solar radiation forecasting models, particularly by enhancing the prediction of solar power production in Saudi Arabia under varying climatic conditions.

ATPAD: An Accessible Tool for Atmospheric Data Processing and Visualization is a Python-based project that enables the analysis and visualization of pre-processed databases in an easy and freely accessible manner. As an example, we apply ATPAD to process and visualize data from the University Network of Atmospheric Observatories (RUOA) of the National Autonomous University of Mexico (UNAM), using three different stations located across Mexico. The access to the analyzed data-set an be found here. For the ATPAD code, please access: https://www.bremex-steaps.net/atpad

\textit{1) Hyrank dataset:}

The dataset was developed with the support of the ISPRS Scientific Committee, taken by the Hyerion sensor carried by NASA's EO-1 satellite. After screening 242 spectral bands from SWIR and VNIR sensors, 176 spectral bands were exported. The total of 5 images and 14 land-cover categories were provided. The Dioni image size is $250 \times1376 $, and the Loukia image size is $249 \times945 $, both with a spatial resolution of 30m. Two scene images are shown in Fig. \ref{Hyrank}.

\textit{2) Houston dataset:}

FLAME2-DT (Forest Fire Detection Dataset with Dual-modality Labels) is a comprehensive multi-modal dataset specifically designed for UAV-based forest fire detection research. The dataset consists of 1,280 paired RGB-thermal infrared images captured by a Mavic 2 Enterprise Advanced UAV system, with high-resolution (640×512) and precise pixel-level annotations for both fire and smoke regions. This dataset addresses critical challenges in forest fire detection by providing paired multi-modal data that captures the complementary characteristics of visible light and thermal imaging.

The dataset used in this study combines remote sensing data from multiple advanced platforms, including Synthetic Aperture Radar (SAR) from Sentinel-1, multispectral imagery from Sentinel-2, and LiDAR measurements from the Global Ecosystem Dynamics Investigation (GEDI) mission. Each of these sources offers unique and complementary information, enabling a detailed and comprehensive analysis of forest canopy height across diverse and ecologically significant regions in northern Vietnam.

Decentralized Collaborative Simultaneous Localization and Mapping (C-SLAM) is essential to enable multi-robot missions in unknown environments without relying on pre-existing localization and communication infrastructure. This technology is anticipated to play a key role in the exploration of the Moon, Mars, and other planets. In this work, we introduce a novel dataset collected during C-SLAM experiments involving three robots operating on a Mars analogue terrain.

Synthetic Aperture Radar (SAR) imagery plays a vital role in identifying flooded areas in the aftermath causing loss of life and significant economic and environmental damage, as water surfaces reflect less microwave energy compared to land due to their smooth texture and low surface roughness.

This dataset is from "One-Stage Cascade Refinement Networks for Infrared Small Target Detection." It includes 427 infrared images and 480 targets (due to the lack of infrared sequences, SIRST also contains infrared images at a wavelength of 950 nm, in addition to shortwave and midwave infrared images). Approximately 90% of the images contain only one target, while about 10% have multiple targets (which may be overlooked in sparse/significant methods due to global unique assumptions).