home.social

#earlywarning — Public Fediverse posts

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

fetched live
  1. AI could transform how we predict hunger and respond to food crises. But a new expert statement warns that algorithms cannot replace human judgement.

    In conflict-affected and data-poor regions, AI-generated information can be incomplete, biased or misleading. Human experts must remain at the heart of life-saving forecasts.

    👉 worldpop.org/blog/experts-call

    #AI #FoodSecurity #HumanitarianAid #EarlyWarning

  2. AI could transform how we predict hunger and respond to food crises. But a new expert statement warns that algorithms cannot replace human judgement.

    In conflict-affected and data-poor regions, AI-generated information can be incomplete, biased or misleading. Human experts must remain at the heart of life-saving forecasts.

    👉 worldpop.org/blog/experts-call

    #AI #FoodSecurity #HumanitarianAid #EarlyWarning

  3. GMIA-NEXT - Next-Generation Global Map of Irrigated Areas |
    --
    doi.org/10.21203/rs.3.rs-10085 <-- shared paper
    --
    zenodo.org/records/17627111 <-- shared open data
    --
    H/T @kyle Davis
    “Irrigation plays a critical role in global food production and climate adaptation and exercises profound influence over humanity's water use. Yet despite its critical importance, there is a persistent lack of understanding of fine-scale irrigation patterns across the planet, knowledge which is essential for informing global food security and sustainability targets. Utilizing either statistical downscaling or remote sensing approaches, existing global irrigation datasets are constrained by coarse spatial resolutions, a lack of timeliness, or varying robustness and reliability. To address this gap, here [they] integrate[d] multi-source Earth observation and environmental datasets and use[d] machine learning to develop a medium-resolution (30 metre) global irrigated area dataset for the 2023/24 growing season. Within existing cropland extent, we leverage a newly compiled set of georeferenced irrigated (N=230,683) and non-irrigated (N=153,194) ground-truth points and integrate seasonal vegetation metrics derived from Landsat 8/9 imagery with agroecological-zone information and hydroclimatic and topographic variables. [They] subsequently develop and evaluate two machine-learning frameworks, a continental Agro-Ecological Zone (AEZ) tile-based framework and a continental-scale framework, and apply the best-performing approach for each continent. Evaluation using held-out test samples yielded a global accuracy of 80.5 ± 2.1%. The resulting maps were also validated against independent global and national irrigation datasets and statistics, demonstrating broad agreement in the spatial distribution of irrigated areas. This approach is robust and reliable because it is built on a harmonized global ground-truth database, incorporates multiple predictors, and is rigorously validated using independent datasets. All code, ground-truth, and data products are freely and publicly available [link above] and can serve as a robust, scale-neutral, and fully reproducible framework for fine-resolution irrigation mapping. These advances provide the critical and long-needed foundation for near-real-time monitoring and early warning systems, and fine-scale land and water resource management…”
    #IrrigatedAreas #Mapping #GIS #spatial #mapping #spatialanalysis #spatiotemporal #global #irrigation #water #hydrology #hydrography #waterresources #farming #agriculture #opendata #remotesensing #earthobservation #geomorphometry #AI #machinelearning #LLM #model #modeling #WaterManagement #opendata #AgroEcologicalZone #AEZ #cropland #irrigatedareas #foodproduction #wateruse #humanimpacts #EarthObservation #remotesensing #earlywarning #monitoring #FoodandAgricultureOrganizationFAO #FAO
    @FAO - Food and Agriculture Organization

  4. GMIA-NEXT - Next-Generation Global Map of Irrigated Areas |
    --
    doi.org/10.21203/rs.3.rs-10085 <-- shared paper
    --
    zenodo.org/records/17627111 <-- shared open data
    --
    H/T @kyle Davis
    “Irrigation plays a critical role in global food production and climate adaptation and exercises profound influence over humanity's water use. Yet despite its critical importance, there is a persistent lack of understanding of fine-scale irrigation patterns across the planet, knowledge which is essential for informing global food security and sustainability targets. Utilizing either statistical downscaling or remote sensing approaches, existing global irrigation datasets are constrained by coarse spatial resolutions, a lack of timeliness, or varying robustness and reliability. To address this gap, here [they] integrate[d] multi-source Earth observation and environmental datasets and use[d] machine learning to develop a medium-resolution (30 metre) global irrigated area dataset for the 2023/24 growing season. Within existing cropland extent, we leverage a newly compiled set of georeferenced irrigated (N=230,683) and non-irrigated (N=153,194) ground-truth points and integrate seasonal vegetation metrics derived from Landsat 8/9 imagery with agroecological-zone information and hydroclimatic and topographic variables. [They] subsequently develop and evaluate two machine-learning frameworks, a continental Agro-Ecological Zone (AEZ) tile-based framework and a continental-scale framework, and apply the best-performing approach for each continent. Evaluation using held-out test samples yielded a global accuracy of 80.5 ± 2.1%. The resulting maps were also validated against independent global and national irrigation datasets and statistics, demonstrating broad agreement in the spatial distribution of irrigated areas. This approach is robust and reliable because it is built on a harmonized global ground-truth database, incorporates multiple predictors, and is rigorously validated using independent datasets. All code, ground-truth, and data products are freely and publicly available [link above] and can serve as a robust, scale-neutral, and fully reproducible framework for fine-resolution irrigation mapping. These advances provide the critical and long-needed foundation for near-real-time monitoring and early warning systems, and fine-scale land and water resource management…”

    @FAO - Food and Agriculture Organization

  5. Milyardan jet hareketlerini izleme sistemimiz, nükleer kriz ve küresel felaket senaryolarını erken tespit ediyor. 🚁🔍 #JetMonitoring #EarlyWarning

    🚩 #JetMonitoring #EarlyWarning #Güvenlik #Teknoloji

  6. Forecasts are improving every year.

    Yet disasters continue to cause massive impacts.

    The real gap is no longer scientific.
    It sits between knowing and deciding.

    Climate resilience today is mostly a governance challenge, not a forecasting one.

    #ClimateRisk #EarlyWarning #ClimateResilience #Weather

  7. O Civic Space Watch nasceu em 2017 para responder ao encolhimento do espaço cívico na Europa. Desde então, cresceu — e a pressão sobre a sociedade civil também.

    Hoje o novo site reúne dados, relatórios, alertas precoces e um espaço dedicado a recursos e ferramentas de proteção para organizações da sociedade civil e defensoras dos direitos humanos.

    @europeancivicforum

    #CivicSpace #HumanRightsDefenders #CivilSociety #Democracy #RuleOfLaw #EarlyWarning #Advocacy #ProtectCivicSpace #NGOs #Europe

  8. 🚨Detection is the name of the game
    🌍Before air defense systems can take action, they need to see the threat
    👀Reliable detection is crucial for safety
    🔒Check our bio for more insights! #EarlyWarning #SensorFusion #ThreatDetection #Surveillance #OpticalTech

  9. 🚀Want to unlock the secrets of next-gen radar?
    🌌It spots threats quicker than a blink!
    👀✨Dive deeper into how this tech is reshaping air defense.
    Check our bio for all the deets!💡🔐
    #EarlyWarning #AESARadar #AirDefense #SignalProcessing #DetectionTech #SituationalAwareness

  10. Multi-Hazard Improves App Retention - Comparison Of Alerting & Attrition For The Multi-Hazards SD Emergency & The Single-Hazard #QuakeAlert
    --
    doi.org/10.1016/j.ijdrr.2025.1 <-- shared paper
    --
    “• Fire is responsible for over 50 % of alerts for County of San Diego, California, USA.
    • App installation rates closely mirror the timing of hazard events.
    • Multi-hazard apps retain users at a 15 % higher rate compared to single-hazard apps.
    • Higher retention improves likelihood people will receive an alert for low-frequency high-impact events like earthquakes..."
    #GIS #spatial #mapping #naturalhazards #Alert #warning #smartphone #userretention #wildfire #SanDiego #California #USA #risk #hazard #mitigation #humanimpacts #socialmedia #push #mobileapps #alerting #earlywarning #warningsystem #multihazard #fire #spatiotemporal #spatialanalysis #earthquake #tsunami #flooding #weather #earlywarning #hazardmanagement #usecase #statistics #events #effect #effectiveness #community #public #infrastructure #loss #damage #cost

  11. Multi-Hazard Improves App Retention - Comparison Of Alerting & Attrition For The Multi-Hazards SD Emergency & The Single-Hazard
    --
    doi.org/10.1016/j.ijdrr.2025.1 <-- shared paper
    --
    “• Fire is responsible for over 50 % of alerts for County of San Diego, California, USA.
    • App installation rates closely mirror the timing of hazard events.
    • Multi-hazard apps retain users at a 15 % higher rate compared to single-hazard apps.
    • Higher retention improves likelihood people will receive an alert for low-frequency high-impact events like earthquakes..."