Add BrightSurf on Google Email

Regional drought prediction from Sentinel-2 time series using Random Forest, DNN, and 1D-CNN: a case study in Marchfeld, Austria

A study proposes an operational framework combining machine learning models with Sentinel-2 data to estimate agricultural drought conditions in irrigated and non-irrigated maize fields. Deep Neural Network (DNN) achieved the best performance, showing higher prediction accuracy and lower error metrics for non-irrigated fields.

SourceBig Earth Data·JournalBig Earth Data·TypeData/statistical analysis·DateJul 26, 2026

Chonnam National University researchers develop new AI system for highly accurate mapping and modeling of orchards

A novel cross-modal fusion framework integrates low-altitude drone RSI with ground robot LiDAR-inertial measurement unit (IMU) odometry to create accurate digital models of orchards. The system achieved localization accuracy on the order of a few centimeters, demonstrating robustness to seasonal variations and long-term drift.

SourceChonnam National University, The Research Information Management Team, Office of Research Promotion·JournalArtificial Intelligence in Agriculture·TypeExperimental study·DateJul 22, 2026

[Research Article] Context-aware landmark recognition in location-based augmented reality: A switching framework with a MobileNet backbone for cultural heritage engagement

A new study proposes a switching-based pervasive augmented reality framework that integrates location-based AR, deep learning, and context-awareness to improve landmark recognition. The framework significantly enhanced detection accuracy compared with conventional LBAR systems, while demonstrating high user satisfaction.

SourceBig Earth Data·JournalBig Earth Data·TypeData/statistical analysis·DateJul 13, 2026

[Research Article] Uncertainty quantification in geospatial AI/ML applications: methods, metrics, and open-source support with an air quality use case

The study systematically evaluates popular Uncertainty Quantification (UQ) methods and metrics for AI/ML-based geospatial applications. It demonstrates that Deep Ensembles and Bayesian Neural Networks achieved the best performance, while highlighting framework-specific differences between TensorFlow and PyTorch.

SourceBig Earth Data·JournalBig Earth Data·TypeData/statistical analysis·DateMay 20, 2026

Call for papers: 10th anniversary special issue of Big Earth Data

The Big Earth Data journal is launching a special issue to reflect on its decade-long impact and showcase cutting-edge advancements in big data research. The journal focuses on Earth-related big data, emerging as a flagship platform at the intersection of Earth science, space science, information science, and sustainability science.

SourceBig Earth Data·JournalBig Earth Data·DateFeb 4, 2026

A new methodology allows for a more precise review of Late Paleolithic portable art and improves the reliability of archaeological interpretations

A new methodology uses photogrammetry and microtopographic analysis to analyze fine engravings in Late Paleolithic portable art, improving the reliability of archaeological interpretations. The technique provides a detailed characterization of groove morphology and variations in depth and width.

SourceUniversitat Jaume I·JournalJournal of Archaeological Science·TypeComputational simulation/modeling·DateFeb 4, 2026

Research Article | Evaluation of ten satellite-based and reanalysis precipitation datasets on a daily basis for Czechia (2001–2021)

A new study evaluates the accuracy of ten satellite-based and reanalysis precipitation datasets using in-situ rain gauge measurements across Czechia from 2001 to 2021. The GSMaP dataset showed superior performance for rainy days, while ERA5-Land overestimated annual precipitation by 15–35%.

SourceBig Earth Data·JournalBig Earth Data·TypeData/statistical analysis·DateJan 23, 2026

Review article | Towards a Global Ground-Based Earth Observatory (GGBEO): Leveraging existing systems and networks

The study presents a comprehensive roadmap for building an integrated GGBEO to meet the United Nations' Sustainable Development Goals and advance climate science. The system would integrate regional and global ground-based in situ and remote sensing systems, marine, and airborne observational data.

SourceBig Earth Data·JournalBig Earth Data·TypeLiterature review·DateDec 15, 2025

First-of-its-kind 3D model lets you explore Easter Island statues up close

A team of researchers from Binghamton University has created the first-ever high-resolution 3D model of Rano Raraku quarry, revealing over 1,000 moai statues. The model allows users to zoom in and pan across various features, providing a detailed look at the island's quarries and challenging previous theories about its history.

SourceBinghamton University·JournalPLOS One·TypeComputational simulation/modeling·DateNov 26, 2025

New global satellite dataset for humanitarian routing and tracking infrastructure change

The new HeiGIT dataset combines PlanetScope imagery with deep-learning models to analyze major transport routes, providing a high-accuracy global classification. The dataset supports better routing for logistics, infrastructure management, and emergency planning, highlighting disparities in road quality and its link to human development.

SourceHeidelberg Institute for Geoinformation Technology·TypeComputational simulation/modeling·DateNov 19, 2025

Hanyang University researchers develop digital twin framework to enhance sustainability and efficiency of modular buildings

Researchers create digital twin facility management system for relocatable modular buildings, improving asset management and decision making. The DT-FMS enhances the lifecycle management of RMBs, minimizing waste and maximizing value through reuse and reconfiguration.

SourceIndustrial Cooperation & research Planning team, Hanyang University ERICA·JournalAutomation in Construction·TypeComputational simulation/modeling·DateAug 14, 2025

First ever assessment reveals accuracy of key maps cocoa companies rely on for environmental compliance

The World Cocoa Foundation and Alliance of Bioversity International assessed the accuracy of key maps for deforestation, tree planting, and greenhouse gas emissions monitoring. The study found that open access global maps are not accurate enough for cocoa analyses in Ghana and Côte d'Ivoire.

When the past meets the future: Innovative drone mapping unlocks secrets of Bronze Age ‘mega fortress’ in the Caucasus

Researchers at Cranfield University used drone mapping to uncover a 3000-year-old mega fortress in the Caucasus, which was found to be significantly larger than initially thought. The site's complex structure and landscape evolution provide new insights into Late Bronze Age and Early Iron Age societies.

SourceCranfield University·JournalAntiquity·TypeObservational study·DateJan 8, 2025

Study reveals the positive link between home kitchens and adolescents’ health

A recent study published in the Journal of Nutrition Education and Behavior reveals a significant influence of home food environments on adolescent dietary patterns. Home food availability, particularly fruits and vegetables, promotes healthier eating habits, while neighborhood fast-food options negatively affect dietary quality.

SourceElsevier·JournalJournal of Nutrition Education and Behavior·TypeData/statistical analysis·DateDec 18, 2024

Rural versus urban divide in eating disorders in Ontario

A new study found that rural regions in Ontario have significantly higher rates of eating disorders among adolescents and young adults. The researchers suggest that stigma and socio-cultural dynamics may contribute to these disparities, highlighting the need for targeted interventions such as telehealth services.

SourceUniversity of Toronto·JournalJournal of Eating Disorders·DateSep 9, 2024

Ready for the storm: FAMU-FSU researchers analyze infrastructure, demographics to see where tornadoes are most disruptive

Researchers used GIS software to analyze data on tornado frequency, transportation infrastructure, and household income to determine where populations are likely to be more resilient. The study's findings can help local governments pinpoint regions with vulnerable communities and fragile transportation networks.

SourceFlorida State University·JournalSustainability·DateMar 13, 2024

Illustrating the relationship between pedestrian movement and urban characteristics using large-scale GPS data

This study uses large-scale GPS data to assess pedestrian movement around Tokyo's stations and its relationship with urban characteristics such as density, diversity, and design. The findings highlight that TOD attributes significantly impact pedestrian count, distances, and durations, but the impact varies across different metrics.

SourceUniversity of Tsukuba·JournalSustainable Cities and Society·DateFeb 6, 2024

Helping more people get to safety in a wildfire

Researchers have developed a new web-based software platform called Wildfire Safe Egress (WISE) that allows emergency planners to design custom-made evacuation plans. The tool uses data on demographics and road networks to simulate wildfire scenarios and calculate safe evacuation probabilities. By analyzing the Camp Fire disaster, rese...

SourceSociety for Risk Analysis·JournalRisk Analysis·DateDec 13, 2023

Scientists create high-resolution poverty maps using big data

A team of researchers from the Complexity Science Hub and Central European University created more-detailed poverty maps for Sierra Leone and Uganda, identifying poor areas with greater accuracy. The maps use a combination of survey information, satellite imagery, and social media data to provide a more accurate picture of wealth distr...

SourceComplexity Science Hub·TypeComputational simulation/modeling·DateApr 30, 2023

Researchers illuminate gaps in public transportation access, equity

A new study by the University of Illinois at Urbana-Champaign reveals that even with broad coverage, public transit systems may still exclude low-income and vulnerable populations. The researchers used a GIS-based approach to evaluate travel times by location and economic conditions, finding that routes often leave behind those who rel...

SourceUniversity of Illinois at Urbana-Champaign, News Bureau·JournalTransportation Research Record Journal of the Transportation Research Board·TypeCase study·DateFeb 16, 2023

UTHSC team’s COVID data system highlighted as model for public health preparedness, population health surveillance

A UTHSC team developed a unique community-focused COVID-19 data registry, MEMPHI-SYS, to guide public health policies and interventions nationwide. The registry collects demographic information, geographic locations, medical history, and risk factors, providing insights into the spread and presentation of COVID.

SourceUniversity of Tennessee Health Science Center·JournalDisaster Medicine and Public Health Preparedness·DateJan 23, 2023

Community study reveals unexpected negative correlation between residential greenspace and psychological well-being of people with spinal cord injury

A study revealed a negative correlation between living in areas with low residential greenspace and lower depressive symptoms among people with spinal cord injury. The findings have implications for urban planning and public policy, highlighting the need to understand how community environment factors influence quality of life.

SourceKessler Foundation·JournalSpinal Cord·TypeSurvey·DateApr 11, 2022

Extreme weather research shows household income impacts of Hurricane Katrina and Superstorm Sandy, need for more equitable climate resilience planning for cities

A new analysis found that low-income households in New Orleans lost nearly 35% of their income after Hurricane Katrina, while high-income households in NYC lost only 5.8%. The study highlights the need for diversified income sources to mitigate economic harm from extreme weather events.

SourceIllinois Institute of Technology·JournalApplied Geography·DateDec 14, 2021

Research links built characteristics of environment with health of persons with SCI

A study published in Archives of Physical Medicine & Rehabilitation found that living in areas with greater mixed land use was associated with poorer perceived health among New Jersey residents with spinal cord injury. This contrasts with general population studies, which suggest benefits from more populated areas with mixed land use.

SourceKessler Foundation·JournalArchives of Physical Medicine and Rehabilitation·DateOct 1, 2015