分享
编辑者： Svitlana Velhush
The embedded tweet could not be found…
Google 與 NASA 噴射推進實驗室開發出一種人工智慧，可從太空追蹤全球甲烷排放。該模型名為 MAPL-EMIT，並在科學期刊《Proceedings of the National Academy of Sciences》上發表。
該工具使用安裝在國際太空站上的 EMIT 光譜儀數據。它能自動偵測並定位甲烷來源，包括羽流重疊的情況。
該模型以 3,6 百萬條經物理模擬的甲烷羽流進行訓練。這使它更能應對複雜地形，並在以往需要人工分析的條件下找出洩漏。
測試結果顯示，MAPL-EMIT 發現的甲烷洩漏比人類專家多 50%。此外，該系統在全球找出超過 23 千條隱藏的羽流，其中包括 24 個來自 25 座最大排放源垃圾掩埋場的羽流。
城市固體廢棄物掩埋場是美國三大主要人為甲烷來源之一。自動化搜尋這類熱點有助於加快有針對性的減緩措施——即針對性的減排。
這項合作延續了 Google 對抗超級污染者的工作。此前，該公司已與 AMP 建立合作夥伴關係，以進行廢棄物處理與碳權產生。
這將如何影響未來幾年全球減少甲烷排放的努力？
Google, NASA launch AI model to map methane emissions from space
OpenAI showed that AI agents can handle the slowest step in modern biology, making sense of huge experiments. By splitting a huge brain experiment among 1,946 AI agents, OpenAI got in 32 minutes what it estimates would take people months: a ranked list of leads for new
GPT-Rosalind surfaced a new lead for drug discovery: could restoring cholesterol transport protect neurons from degeneration? DCTN1 is a gene linked to Perry syndrome, a rare neurodegenerative disorder. In mouse-brain data, disrupting it increased expression of genes involved in
🔸 €3.4 billion for 77 net-zero technology projects through our Innovation Fund 🔸 Over €390 million for 135 climate and environment projects through our LIFE programme
EU weakens call for ban on Arctic oil and gas drilling 🔷 EU removes call for multilateral drilling ban 🔷 Continues to call for oil, gas to be left in ground 🔷 Follows Norwegian lobbying, Ukraine, Iran wars okt.to/v2TiNe
