home.social

#geostatistics — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #geostatistics, aggregated by home.social.

  1. Mapping Flood Agents In The Northern Pantanal Wetland Using Multiple Spatio-Temporal GIS And Remote Sensing Techniques
    --
    doi.org/10.1007/s13157-026-020 <-- shared paper
    --
    H/T @renato Gatto de Morais | Geógrafo | Mestre em Recursos Hídricos | Doutorando em Geografia
    “Combining MODIS data, TRMM, river discharge, a digital terrain model, and multinomial logistic regression, [the authors] identified three predominant classes of flood origin: local rainfall, bank overflow, and mixed areas. The model achieved a Nagelkerke Pseudo-R² of 0.63 and a classification accuracy of up to 81.2% (10-fold cross-validation). To the best of [their] knowledge, this is the first explicit approach to mapping flood agents for this wetland, a component that has historically remained unmapped despite its recognized influence on habitats and biodiversity…”
    --
    “The mapping of functional hydrologic units is crucial for enhancing our understanding of flooding and hydroecological processes in large wetlands. These units are typically defined by flooding frequency, duration, and magnitude, but another important hydrologic characteristic is the origin of flooding, known as the flood agent. This study presents an empirical framework utilizing remote sensing and GIS procedures for modeling flood agents in the northern Pantanal wetland. Eleven spatial data layers were derived from multi-year MODIS flood maps, daily rainfall estimates from the TRMM 3B42 grid, in situ discharge data, the BEST Digital Terrain Model, and a hydrographic network layer. These layers were tested for their predictive power in a multinomial logistic regression mapping model. Model performance metrics, along with qualitative validation of mapping outcomes using in situ flooding measurements, and vegetation and soil data from field test sites, support the plausibility of the proposed mapping scheme. However, they also highlight the challenges of flood agent mapping in large tropical wetlands…”
    #GIS #spatial #mapping #MODIS #TRMM #riverdischarge #digitalterrainmodel #multinomiallogisticregression #geostatistics #Pantanal #Cuiaba #Brazil #water #hydrology #spatialanalysis #spatiotemporal #remotesensing #earthobservation #flood #flooding #source #type #floodagent #tropical #wetland #habitat #biodiversity #ecosystem #hydrologicunit #hydroecology #model #modeling #rainfall #precipitation #weather #climate #discharge #network #metrics

  2. Using Geospatial Analysis and Explainable Machine Learning to Examine Risk Factors of Out-of-Hospital Cardiac Arrest Survival Outcome
    --
    openscholar.uga.edu/record/269 <-- shared technical publication / dissertation
    --
    aag.org/award-grant/william-l- <-- shared @AAG William L. Garrison Award for Best Dissertation in Computational Geography
    --
    [again, way outside any expertise I might have, but fascinating spatial analysis use case…]
    H/T @Jielu Zhang | Postdoctoral Researcher @ Harvard University
    “[The authors] Ph.D. dissertation "Using Geospatial Analysis and Explainable Machine Learning to Examine Risk Factors of Out-of-Hospital Cardiac Arrest Survival Outcome" [1st link above] has received the 2026 biennial William L. Garrison Award for Best Dissertation in Computational Geography from the American Association of Geographers… [2nd link above.]
    In [their] research, [they] develop[ed] Explainable GeoAI and Causal GeoAI methods that combine geographic data and artificial intelligence to expose and ameliorate health disparities by delivering models that not only predict risks but also illuminate how and where to intervene. While [their] dissertation focused on cardiovascular disease, these approaches are broadly applicable to public health, medicine, urban planning, environmental exposure, and resilience research…”
    #explainable #causal #AI #model #modeling #PublicHealth #GIS #spatial #mapping #spatialanalysis #spatiotemporal #AAG2026 #AAG #Award #geostatistics #Georgia #health #risk #hazard #cardiacarrest #cardiovacscular #usecase #metrics #midocine #urbanplanning #resilience #survival #OutofHospital #PhD #Dissertation #CardiacArrest #AutomatedExternalDefibrillator #SpatialOptimization #GeographicallyExplainableArtificialIntelligence #GeoAI #GeoXAI #SpatiallyAwareCausalInference #OverlayedSpatioTemporalOptimization #healthcare #medical #intervention #GIS #spatial #mappingt #spatialanalysis #spatiotemporal #heart #heartattack #AED #survival #survivaloutcomes #machinelearning #AI #publichealth #healthgeographers #counterfactual #explainable #deeplearning #model #modeling

  3. Challenges In Comparing National Forest Statistics - Canada As A Case Study
    --
    📑 pubs.cif-ifc.org/doi/abs/10.55 <-- shared paper
    --
    H/T Michael Wulder |Senior Research Scientist at Natural Resources Canada
    “Canada is a forest nation. Its forests are spatially extensive, ecologically diverse, and of global importance. While national level forest statistics are used for international reporting and comparison, they often fail to reflect the distinctive structure and stewardship context of Canada’s forest estate, which includes millions of hectares of remote, unmanaged forests alongside actively managed zones governed by provincial and territorial stewardship frameworks...”
    --
    #forest #Canada #national #geostatistics #forestestate #remote #unmanaged #contrast #managed #harvesting #naturalresources #resource #spatialanalysis #spatiotemporal #GIS #spatial #mapping #assessment #value #metrics #stewardship #management #monitoring #statistics #health #foresthealth #science
    #NRCAN #NRCANScience #NaturalResourcesCanada