Mastodawn

AI maps deep-sea coral reefs from archived underwater footage: A new project uses AI to analyze thousands of hours of seafloor video, producing the first comprehensive maps of vulnerable marine ecosystems across the Atlantic basin. https://theconversation.com/how-ai-could-unlock-deep-sea-secrets-of-marine-life-276717 #AIagent #AI #GenAI #ClimateAI

How AI could unlock deep-sea secrets of marine life

Robotic and autonomous underwater vehicles have collected vast quantities of footage from the deep sea, but most of it hasn’t been analysed.

The Conversation

GreenPT Feb 26

Climate work is entering its AI era.

We are proudly partnering with Kith Climate and Kith AI Labs.

Kith prepares climate professionals to use AI with confidence and impact.

As Ben Hillier, founder of Kith, shares:
“We’ve chosen to partner with GreenPT due to our clear alignment around the value of AI for climate professionals and the need to deploy AI in an environmentally conscious way.”

Together, we combine AI capability with responsible deployment.

#ClimateAI #GreenAI

sayzard Jan 29

Python Trending (@pythontrending)

earth2studio는 AI 기반 기상·기후 워크플로우를 탐색·구축·배포하기 위한 오픈소스 딥러닝 프레임워크로 소개됩니다. 기상·기후 데이터를 활용한 모델 개발과 배포 파이프라인을 지원하는 도구로, 연구자와 엔지니어가 기후 관련 AI 워크플로우를 쉽게 실험·운영할 수 있도록 설계된 프로젝트입니다.

https://x.com/pythontrending/status/2016468200020406370

#earth2studio #opensource #climateai #deeplearning

Python Trending 🇺🇦 (@pythontrending) on X

earth2studio - Open-source deep-learning framework for exploring, building and deploying AI weather/climate workflows. https://t.co/yz8AGH9g3d

X (formerly Twitter)

Tim Green Jan 18

Google DeepMind's new AI model accelerates hurricane forecasting with greater speed and accuracy, potentially saving lives and reducing damage through faster, less costly predictions. A major breakthrough in AI-powered climate resilience. Read more: https://www.theguardian.com/technology/artificialintelligenceai #ClimateAI

AI (artificial intelligence) | The Guardian

Latest news, sport, business, comment, analysis and reviews from the Guardian, the world's leading liberal voice

Levent Kurnaz Dec 28

New research shows drought forecasts improve dramatically when climate data is decomposed before modelling. Better tools mean earlier warnings and smarter water management.
#Drought #ClimateAI #WaterSecurity
https://link.springer.com/article/10.1007/s11600-025-01773-5

Investigating the contribution of decomposition techniques to machine learning accuracy in SPEI-based drought forecasting for multiple Köppen-Geiger climates - Acta Geophysica

Drought is a disaster that affects everything related to humans, particularly the economy. Therefore, predicting its effects before they occur is crucial. However, due to its nature, droughts are more challenging to detect than other natural disasters. This study aims to investigate the effect of decomposition techniques (VMD, DWT, EMD, and EEMD) on the drought forecasting performance of machine learning methods (network-based: MLP, KAN, RNN, BiLSTM, and BiGRU, as well as tree-based methods: RF, GB, XGB, AB, and M5P) in different climate types. To this end, the Standardised Precipitation Evapotranspiration Index (SPEI), which was calculated using 52 years of precipitation and temperature values from 1969 to 2020 for three meteorological stations in Türkiye with different Köppen-Geiger climate classifications, was employed. Drought predictions were made for three SPEI time scales: 3, 6, and 12 months. The results of the analysis revealed that decomposition increased the power of prediction compared to raw drought data, and VMD was the most effective decomposition technique. For instance, the NSE values, which was approximately 0.5 in SPEI-3, 0.7 in SPEI-6, and 0.9 in SPEI-12, increased to above 0.95 across all time scales following the implementation of the VMD method to different climate types. Besides, MLP, KAN, and M5P proved to be the most effective machine learning methods with this value above 0.98 in all data sets. Performance improved as the time scale increased in recurrent neural network-based methods (RNN, BiLSTM, and BiGRU). Consequently, irrespective of the climate region, models employing the decomposition method (VMD and DWT) exhibited considerably enhanced performance.

SpringerLink