Population distribution data with high spatiotemporal resolution are of significant value and fundamental to many application areas, such as public health, urban planning, environmental change, disaster management. However, still not widely available due the limited knowledge complex human activity patterns. The emergence location-based service big provides additional opportunities solve this problem. In study, we integrated ambient population data, nighttime light building volume data;...

Abstract Urban populations face heightened extreme heat risks attributed to urban islands and high population densities. Although previous studies have examined global exposure heatwaves, the influence of urbanization-induced warming is still not quantified. Here, leveraging satellite-derived near-surface air temperature data, we assess impacts on in 1028 cities worldwide. Additionally, investigate its role shaping disparities between North South cities. Our findings reveal that...

Building shadows (BSs) frequently occur in urban areas, and their area distribution display strong seasonal variations that significantly influence the land surface temperature (LST). However, it remains unclear how BSs affect LST at city scale because is difficult to extract shaded subpixel connect such areas with pixel scale. In this study, we combined sun angle, building height, footprint occlusion spatial of central Beijing. The effect on was analyzed using retrieved from Landsat-8...

Aquaculture plays a key role in achieving Sustainable Development Goals (SDGs), while it is difficult to accurately extract single-object aquaculture ponds (SOAPs) from medium-resolution remote sensing images (Mr-RSIs). Due the limited spatial resolutions of Mr-RSIs, most studies have aimed obtain areas rather than SOAPs. This study proposed an object-oriented method for extracting We developed iterative algorithm combining grayscale morphology and edge detection segment water bodies...

Abstract Rapid building damage assessment following an earthquake is important for humanitarian relief and disaster emergency responses. In February 2023, two magnitude-7.8 earthquakes struck Turkey in quick succession, impacting over 30 major cities across nearly 300 km. A comprehensive understanding of the distribution essential efficiently deploying rescue forces during critical periods. This article presents training a two-stage convolutional neural network called BDANet that integrated...

AbstractThe vegetation health index (VHI) is a widely utilized remote-sensing-based for monitoring agricultural drought on the regional or global scale. However, validity of VHI as detection tool relies assumption that normalized difference (NDVI) and land-surface temperature (Ts) at given pixel will vary inversely over time. This may introduce large uncertainties in areas with complex landforms, such China. In order to monitor whole China, new suggested this article, termed (VDI). VDI...

Earthquakes are unpredictable and potentially destructive natural disasters that take a long time to recover from. Monitoring post-earthquake human activity (HA) is of great significance recovery reconstruction work. There strong correlation between night-time light (NTL) HA, which aid in the study spatiotemporal changes activities. However, seasonal noise impact from National Polar-Orbiting Partnership Satellite Visible Infrared Imaging Radiometer Suite (NPP/VIIRS) data greatly limits their...

Accurate spatial population distribution information, especially for metropolises, is of significant value and fundamental to many application areas such as public health, urban development planning disaster assessment management. Random forest the most widely used model in spatialization studies. However, a reliable accurately mapping metropolitan populations still lacking due inherent limitations random complexity problem. In this study, we integrate gradient boosting decision tree (GBDT),...

The normalized difference vegetation index (NDVI) is one of the most common metrics used to describe dynamics. Unfortunately, low-quality pixels resulting from contamination (by features including clouds, snow, aerosols, and mixed factors) have impeded NDVI products’ widespread application. Researchers thought several ways improve quality when occurs. However, these algorithms are based on noise-negative deviation principle, which aligns low-value products an upper line but ignores cases...

Forest fires are characterized by a rapid and devastating nature, underscoring the practical significance of forest fire risk monitoring. Currently, assessments inadequately account for non-meteorological hazard factors, lack hazard-formative environment contextual disaster knowledge occurrence mechanisms. In response, based on MODIS products, we augmented FFDI (forest danger index) with RDST (regional system theory) selected various indicators, including lightning. MOD14 was used...

High spatiotemporal resolution land surface temperature (LST) plays an important role in various environment applications. However, the limitation of thermal infrared sensors and effect clouds other atmospheric conditions result discontinuous daily observations Moderate Resolution Imaging Spectroradiometer (MODIS). Annual cycle (ATC) models can help to supply continuous LSTs via limited observations, but these ATC seldom consider disturbance weather or cover change. On hand, spatial...

Understanding the winter wheat yield responses to drought are keys minimizing drought-related losses under climate change. The research goal of our study is explore response patterns in North China Plain (NCP) and then further which climatic factors drive patterns. For this purpose, was simulated by Environmental Policy Integrated Climate (EPIC) crop model. Drought quantified standardized precipitation evapotranspiration index (SPEI), contributions various were evaluated using predictive...

Water conservation is an important service function of ecosystems. A timely understanding dynamic changes in the water for protection and reconstruction resources. Based on remote sensing data, meteorological land cover "Technical Criterion Ecosystem Status Evaluation" issued by Ministry Environmental Protection People's Republic China, a comprehensive evaluation system was designed to assess Xiongan New Area from 2005 2015. The created four aspects, including ecological structure, stress,...

The Sendai Framework for Disaster Risk Reduction 2015–2030 (SFDRR) proposed seven targets comprising 38 quantified indicators and various sub-indicators to monitor the progress of disaster risk loss reduction efforts. However, challenges persist regarding availability disaster-related data required resources address gaps. A promising way this issue is utilization Earth observation (EO). In study, we an EO-based evaluation framework in service SFDRR applied it context tropical cyclones (TCs)....

Early detection of forest fire is helpful for monitoring the spread promptly, minimizing loss forests, wild animals, human life, and economy. The performance brightness temperature (BT) prediction determines accuracy detection. Great efforts have been made on BT model building, but there still remains some uncertainty. Based widely used contextual (CM) temporal-contextual (TCM), we proposed a spatio-temporal (STCM), which involves historical images to contrast correlation matrix between...

The evaluation of mortality in earthquake-stricken areas is vital for the emergency response during rescue operations. Hence, an effective and universal approach accurately predicting number casualties due to earthquake needed. To obtain a precise casualty prediction method that can be applied regions with different geographical environments, spatial division based on regional differences zoning support vector regression (SVR) are proposed this study. This study comprises three parts: (1)...

Typically, object-based classification methods are learned using training samples with labels attached to image objects. In this letter, a semisupervised method in the framework of topic modeling is proposed classify very high resolution panchromatic satellite images partially labeled pixels. stage training, both topics and their co-occurred distributions an unsupervised manner from segmented images. Meanwhile, unlabeled pixels allocated user-provided geo-object class based on model....

Aquaculture mapping is essential for monitoring and managing aquaculture resources. However, accurately geotargeting individual ponds from medium-resolution remote sensing imagery remains challenging, convolutional deep learning methods identifying require labor-intensive pixel-level annotations. This paper presents a novel weakly-supervised method to derive labels image-level annotations ponds. Our approach uses iterative anti-adversarial attacks refine localization results multi-scale...