{"@context":"https://schema.org","@type":"NewsArticle","generatedAt":"2026-09-21T16:01:09.055Z","headline":"Google 与 NASA JPL 发布 MAPL-EMIT 深度学习框架，用卫星高光谱数据绘制全球甲烷排放","description":"Google 与 NASA JPL 在 PNAS 发表 MAPL-EMIT，一个基于 Swin-S vision transformer 的深度学习框架，可自动化检测、量化甲烷羽流并定位排放源。","url":"https://www.aioga.com/news/cmtj3dl5b04raroh9axj6ugai/","mainEntityOfPage":"https://www.aioga.com/news/cmtj3dl5b04raroh9axj6ugai/","datePublished":"2026-09-01T20:00:26.000Z","dateModified":"2026-09-01T20:00:26.000Z","inLanguage":"zh-CN","publisher":{"@type":"NewsMediaOrganization","name":"Aioga","url":"https://www.aioga.com"},"citation":["https://research.google/blog/mapping-global-methane-emissions-from-space-with-deep-learning","https://aihot.virxact.com/items/cmtj3dl5b04raroh9axj6ugai"],"canonicalUrl":"https://www.aioga.com/news/cmtj3dl5b04raroh9axj6ugai/","directAnswer":{"@type":"Answer","text":"Google 与 NASA JPL 在 PNAS 发表 MAPL-EMIT。该框架基于 Swin-S 视觉 Transformer，可处理 EMIT 高光谱数据，自动检测和量化甲烷羽流，并估计排放源位置。","url":"https://www.aioga.com/news/cmtj3dl5b04raroh9axj6ugai/","dateCreated":"2026-09-01T20:00:26.000Z","author":{"@type":"Organization","@id":"https://www.aioga.com/authors/aioga-editorial/#editorial-team","name":"Aioga Editorial Team","url":"https://www.aioga.com/authors/aioga-editorial/"}},"evidence":[{"@type":"CreativeWork","name":"Google Research：Blog（网页） source article","url":"https://research.google/blog/mapping-global-methane-emissions-from-space-with-deep-learning","datePublished":"2026-09-01T20:00:26.000Z","provider":{"@type":"Organization","name":"Google Research：Blog（网页）","url":"https://research.google/blog/mapping-global-methane-emissions-from-space-with-deep-learning"}},{"@type":"CreativeWork","name":"AIHot archive record","url":"https://aihot.virxact.com/items/cmtj3dl5b04raroh9axj6ugai","datePublished":"2026-09-01T20:00:26.000Z","provider":{"@type":"Organization","name":"AIHot","url":"https://aihot.virxact.com/items/cmtj3dl5b04raroh9axj6ugai"}}],"aggregationSource":"Google Research：Blog（网页）","originalPublisher":{"name":"Google Research：Blog（网页）","url":"https://research.google/blog/mapping-global-methane-emissions-from-space-with-deep-learning"},"geoDeepAnswer":null,"article":{"id":"cmtj3dl5b04raroh9axj6ugai","slug":"cmtj3dl5b04raroh9axj6ugai","url":"https://www.aioga.com/news/cmtj3dl5b04raroh9axj6ugai/","title":"Google 与 NASA JPL 发布 MAPL-EMIT 深度学习框架，用卫星高光谱数据绘制全球甲烷排放","title_en":"","summary":"Google 与 NASA JPL 在 PNAS 发表 MAPL-EMIT，一个基于 Swin-S vision transformer 的深度学习框架，可自动化检测、量化甲烷羽流并定位排放源。","source":"Google Research：Blog（网页）","sourceUrl":"https://research.google/blog/mapping-global-methane-emissions-from-space-with-deep-learning","aiHotUrl":"https://aihot.virxact.com/items/cmtj3dl5b04raroh9axj6ugai","publishedAt":"2026-09-01T20:00:26.000Z","category":"行业动态","score":58,"selected":false,"articleBody":["Vishal Batchu, Research Engineer, and Michelangelo Conserva, Research Scientist, Google Research","The Methane Analysis and Plume Localization with EMIT model is a deep-learning framework that automates the detection, enhancement quantification, and source estimation of methane plumes globally, turning raw satellite data into scalable climate action.","Methane：https://en.wikipedia.org/wiki/Methane is a potent greenhouse gas; over a 100-year timeframe, its warming potential is 30 times：https://www.ipcc.ch/assessment-report/ar6/ greater than that of carbon dioxide. In fact, it has driven approximately 25% of human-induced warming：https://www.ipcc.ch/assessment-report/ar6/ since the start of the industrial era. Because methane has a relatively short atmospheric lifespan, promptly reducing these emissions offers a critical \"fast-action\" pathway to mitigating global temperature rise.","This urgency is reflected in the Global Methane Pledge：https://www.globalmethanepledge.org/, where over 125 countries have committed to a 30% emissions reduction by 2030. To hit these targets, we must empower stakeholders to track localized point sources (emissions occurring from a small spatial footprint on the order of a few tens of meters) across the waste, agriculture, and energy sectors. The most cost-effective strategies are to mitigate emissions from oil and gas infrastructure, agricultural facilities, and landfills.","To track these emissions on a global scale, scientists increasingly rely on space-based imaging. A prime example is NASA’s Earth Surface Mineral Dust Source Investigation：https://earth.jpl.nasa.gov/emit/ (EMIT) instrument on the International Space Station. While originally designed to map mineral composition in arid regions, scientists at NASA’s Jet Propulsion Laboratory：https://www.jpl.nasa.gov/ (JPL) and the broader scientific community have leveraged EMIT's advanced hyperspectral：https://en.wikipedia.org/wiki/Hyperspectral_imaging capabilities to detect methane emissions. By recording hundreds of distinct bands of light for every pixel, it allows researchers to \"see\" the unique chemical fingerprints of these otherwise invisible gases.","A global view of methane detections from space. As we zoom in, the MAPL-EMIT model highlights specific methane plumes, revealing critical details such as source location.","Measuring methane from space requires balancing three key factors: (1) field of view (spatial coverage/revisit), (2) spatial resolution, and (3) spectral resolution.","Global mappers like TROPOMI：https://www.tropomi.eu/ were designed to detect small changes in background methane concentrations by integrating high coverage (approximately 2,600 km swath width), coarse spatial resolution (around 5.5 km x 3.5 km), and fine spectral sampling (0.1 nm).","In contrast, point source mappers like EMIT excel at measuring methane emissions at the facility scale. They achieve this by combining moderate coverage (an 80 km wide field of view) with very high spatial resolution (60 meters) and a moderate spectral resolution (7.4 nm spectral sampling), sufficient to capture the chemical signature of methane at a high signal to noise ratio.","However, fully unlocking the potential of this rich data at a global scale presents additional challenges. The Earth's varied landscapes provide a complex backdrop, and some surface materials can masquerade as methane, making the identification of smaller or more diffuse sources particularly challenging. To build on the EMIT team's foundational work and enable high-throughput global mapping, we collaborate with them to apply deep-learning models that can understand the broader visual context of the scene.","This work aligns with Google’s broader effort behind Google Earth AI：https://ai.google/earth-ai/, our collection of geospatial models and datasets to turn planetary data into actionable intelligence. By applying deep learning to satellite imagery at scale, we aim to complement broader planetary AI initiatives with specialized tools for targeted environmental monitoring.","Spotting the invisible. This comparison demonstrates the challenge of methane detection: standard visible imagery shows no gas, NASA L2B enhancements ：https://www.earthdata.nasa.gov/data/catalog/lpcloud-emitl2bch4enh-002 (from matched filter) reveal a noisy signal, but the MAPL-EMIT model clearly isolates the methane plume from the background landscape.","We built MAPL-EMIT using an end-to-end vision transformer architecture (Swin-S transformer：https://arxiv.org/abs/2103.14030). While many approaches analyze hyperspectral data on a pixel-by-pixel basis, MAPL-EMIT leverages modern computer vision techniques to process the complete spectrum of light alongside its surrounding spatial context. By analyzing how gas disperses across the landscape, the model is better equipped to distinguish a true, wind-blown methane plume (a trail of methane gas dispersing from a specific source) from a patch of ground that simply shares a similar spectral signature, which has historically caused false methane detections.","Crucially, this spatial awareness empowers the model to untangle highly complex scenes. In dense industrial regions, emissions from multiple neighboring facilities often merge into a single cloud. To make sense of these scenarios, MAPL-EMIT simultaneously solves three distinct tasks:","Disentangling complex emissions. By analyzing spatial context, MAPL-EMIT simultaneously delineates the exact shape of multiple, overlapping methane plumes and pinpoints their respective source origins (marked with an X), even in dense industrial regions.","Transformer-based models require massive amounts of data to learn, but a global, labeled dataset of millions of real-world methane emissions simply doesn't exist. To overcome this, we developed a physics-based simulation framework. We created 3.6 million synthetic methane plumes and injected them directly into real EMIT scenes. By using Lagrangian puff models：https://www.nature.com/nature-index/topics/l4/lagrangian-particle-dispersion-modeling-in-atmospheric-studies, which simulate how particles move and disperse through the air, we were able to recreate the chaotic, turbulent reality of actual gas emissions. Training on these highly realistic simulations allowed MAPL-EMIT to learn to spot methane under a vast variety of atmospheric and geographic conditions. This synthetic training approach provided several key advantages:","Training with synthetic reality. Because millions of labeled, real-world methane plumes do not exist, we trained the model by injecting physics-based simulated plumes, representing diverse emission rates and turbulent atmospheric conditions, directly into real EMIT hyperspectral scenes.","Deployed on real-world satellite data, MAPL-EMIT demonstrates strong potential for scalable emissions mapping. Upon benchmarking against NASA's gold-standard L2B methane plumes dataset：https://www.earthdata.nasa.gov/data/catalog/lpcloud-emitl2bch4plm-002, the model captures 84% of expert-annotated plumes and identifies around 50% more plausible plumes across ~1100 EMIT granules, showcasing its ability to separate subtle signals from background noise. See the paper：https://www.pnas.org/doi/10.1073/pnas.2612145123 for more details.","This increased sensitivity also allows MAPL-EMIT to reliably capture weaker emissions, improving on current detection limits. The model also proved robust in complex environments, successfully mapping plumes at 24 of the world's 25 top-emitting landfills.","As with many highly sensitive models, false positives remain an ongoing challenge, particularly in complex terrain. To help mitigate this, outputs are paired with physics-based plume confidence (spectral fit) scores：https://www.sciencedirect.com/science/article/pii/S0034425725002640, assessed based on the number of detections over strided inference, and evaluated using multiple other properties, enabling users to filter and trade off between the ability to capture real plumes and the risk of false positives as they see fit. However this isn’t always straightforward, which is why we also tag each plume with a “lower” or “higher” confidence based on these properties, allowing users to directly use the data.","Tracking persistent emissions over time. A time-series of MAPL-EMIT methane detections successfully capturing plumes originating from a major landfill in Amman, Jordan, demonstrating the model's high sensitivity and robustness in complex environments.","MAPL-EMIT showcases a powerful collaboration, bringing together Google's machine learning expertise with the domain knowledge of our collaborators at NASA JPL. Together, we are advancing the full potential of space-based methane observations at the facility scale, providing the global community with the tools necessary to enable meaningful action on reducing greenhouse gas emissions.","We would like to thank individuals across Google and NASA JPL who carried out this work and made the launch possible, including (in alphabetical order): Alex Wilson, Anna M. Michalak , Varun Gulshan, Philip G. Brodrick, Andrew K. Thorpe, Christopher V. Arsdale, Burak Ekim, Carl Elkin, Tal Geller, Omry Gillon, Nita Goyal, Mansi Kansal, Roy Nadler, John Platt, Sergei Shames, Bijoy Shetty, Aaron Sonabend, Deepika Sukhija, Shahar Timnat, Maxim Neumann, Anton Raichuk, Frances Reuland, Adam R. Brandt, David R. Thompson, Robert O. Green, Jay Radzinski, Vishal V. Batchu, and Michelangelo Conserva."],"articleImages":[],"mediaStatus":"none","articleBodyZh":["谷歌研究院研究工程师Vishal Batchu和研究科学家Michelangelo Conserva。","甲烷分析与羽流定位与EMIT模型是一种深度学习框架，能够自动化全球范围内甲烷羽流的检测、增强量化和源估计，将原始卫星数据转化为可扩展的气候行动。","甲烷：https：//en.wikipedia.org/wiki/甲烷是一种强效温室气体;在100年的时间范围内，其变暖潜力是二氧化碳的30倍：https：//www.ipcc.ch/assessment-report/ar6/。事实上，自工业时代开始以来，甲烷推动了约25%的人为变暖：https：//www.ipcc.ch/assessment-report/ar6/。由于甲烷的大气寿命相对较短，及时减少这些排放为缓解全球气温上升提供了关键的“快速行动”途径。","这一紧迫性体现在全球甲烷承诺：https：//www.globalmethanepledge.org/ 中，已有125多个国家承诺到2030年减少30%的排放。为实现这些目标，我们必须赋能利益相关者追踪废弃物、农业和能源领域的局部点源（仅数十米空间足迹产生的排放）。最具成本效益的策略是减少石油和天然气基础设施、农业设施和垃圾填埋场的排放。","为了在全球范围内追踪这些排放，科学家们越来越依赖基于空间的成像技术。一个典型例子是美国宇航局（NASA）国际空间站上的地表矿物尘埃源调查仪：https：//earth.jpl.nasa.gov/emit/（EMIT）。虽然最初设计用于绘制干旱地区的矿物成分，但NASA喷气推进实验室（JPL）的科学家们利用了EMIT先进的高光谱技术（https：//en.wikipedia.org/wiki/Hyperspectral_imaging 能力来探测甲烷排放。通过记录每个像素数百条不同的光带，研究人员能够“看到”这些原本不可见气体独特的化学指纹。","从太空观察甲烷检测的全球视图。当我们逐渐放大时，MAPL-EMIT 模型会突出显示特定的甲烷羽流，揭示关键细节，例如来源位置。","从太空测量甲烷需要在三个关键因素之间取得平衡：（1）视野（空间覆盖/重访），（2）空间分辨率，以及（3）光谱分辨率。","全球测绘器如 TROPOMI：https://www.tropomi.eu/ 被设计用于通过集成高覆盖范围（约 2,600 公里扫描宽度）、粗空间分辨率（约 5.5 公里 x 3.5 公里）和精细光谱采样（0.1 纳米）来检测背景甲烷浓度的微小变化。","相比之下，点源测绘器如 EMIT 擅长在设施尺度上测量甲烷排放。它们通过将中等覆盖范围（80 公里宽视野）与极高空间分辨率（60 米）和中等光谱分辨率（7.4 纳米光谱采样）结合，实现高信噪比捕捉甲烷的化学特征。","然而，要在全球范围内充分释放这些丰富数据的潜力，还面临额外挑战。地球多样的景观提供了复杂的背景，而一些地表材料可能伪装成甲烷，使得识别较小或较分散的源尤其具有挑战性。为了在 EMIT 团队的基础工作上进一步发展并实现高通量全球测绘，我们与他们合作，应用能够理解场景更广泛视觉上下文的深度学习模型。","这项工作与谷歌在 Google Earth AI：https://ai.google/earth-ai/ 背后的更广泛努力一致，这是我们收集的地理空间模型和数据集，旨在将行星数据转化为可操作的情报。通过大规模将深度学习应用于卫星影像，我们希望用专门工具补充更广泛的行星 AI 项目，用于针对性环境监测。","发现隐形之物。该比较展示了甲烷检测的挑战：标准可见光影像未显示气体，NASA L2B 增强：https://www.earthdata.nasa.gov/data/catalog/lpcloud-emitl2bch4enh-002（基于匹配滤波器）显示噪声信号，但 MAPL-EMIT 模型清晰地将甲烷羽流从背景景观中分离出来。","我们使用端到端视觉变换器架构（Swin-S transformer：https://arxiv.org/abs/2103.14030）构建了 MAPL-EMIT。虽然许多方法是逐像素分析高光谱数据，但 MAPL-EMIT 利用现代计算机视觉技术处理完整的光谱信息及其周围的空间上下文。通过分析气体在景观中的扩散方式，该模型能够更好地区分真正的风吹甲烷羽流（来自特定源的甲烷气体扩散轨迹）和仅仅具有相似光谱特征的地面区域，这在过去常导致甲烷误检。","关键是，这种空间意识使模型能够解开高度复杂的场景。在密集的工业区域，多个相邻设施的排放物经常混合成一个单一的云层。为了理解这些情景，MAPL-EMIT 同时解决三个不同的任务：","解开复杂排放。通过分析空间上下文，MAPL-EMIT 能够同时描绘多重重叠的甲烷羽流的精确形状，并定位其各自的来源（用 X 标记），即使在密集的工业区域也能做到。","基于变换器的模型需要海量数据来学习，但全球范围内包含数百万真实甲烷排放的标注数据集根本不存在。为克服这一问题，我们开发了基于物理的模拟框架。我们创建了 360 万个合成甲烷羽流，并将其直接注入到真实的 EMIT 场景中。通过使用拉格朗日烟羽模型：https://www.nature.com/nature-index/topics/l4/lagrangian-particle-dispersion-modeling-in-atmospheric-studies，该模型模拟了颗粒在空气中的运动和扩散，我们能够重现实际气体排放的混乱和湍流现实。基于这些高度逼真的模拟进行训练，使 MAPL-EMIT 学会在各种大气和地理条件下检测甲烷。这种合成训练方法提供了几个关键优势：","使用合成现实进行训练。由于不存在数百万个带标签的真实甲烷羽流，我们通过将基于物理模拟的羽流（代表不同的排放速率和湍流大气条件）直接注入真实的 EMIT 高光谱场景来训练模型。","在实际卫星数据上的应用表明，MAPL-EMIT 在可扩展排放映射方面显示出强大的潜力。在与 NASA 的黄金标准 L2B 甲烷羽流数据集（https://www.earthdata.nasa.gov/data/catalog/lpcloud-emitl2bch4plm-002）进行基准测试时，该模型捕捉到了 84% 的专家标注羽流，并在约 1100 个 EMIT 数据块中识别出约多 50% 的合理羽流，展示了其从背景噪声中分离微弱信号的能力。更多细节请参见论文：https://www.pnas.org/doi/10.1073/pnas.2612145123。","这种增强的灵敏度还使 MAPL-EMIT 能够可靠地捕捉较弱排放，改进了现有检测极限。该模型在复杂环境中也表现出了稳健性，成功绘制了全球 25 个排放量最高的垃圾填埋场中的 24 个的羽流。","与许多高灵敏度模型一样，假阳性仍然是一个持续的挑战，尤其是在复杂地形中。为帮助缓解这一问题，输出结果与基于物理的羽流置信度（光谱拟合）评分（https://www.sciencedirect.com/science/article/pii/S0034425725002640）配对，根据跨步推理的检测次数进行评估，并使用多种其他属性进行评估，使用户能够根据需要筛选并在捕捉真实羽流能力与假阳性风险之间进行权衡。然而，这并非总是直观的，因此我们还根据这些属性为每个羽流标记“低”或“高”置信度，使用户能够直接使用数据。","追踪持续排放随时间的变化。MAPL-EMIT 甲烷检测的时间序列成功捕捉了来自约旦安曼一处主要垃圾填埋场的羽流，展示了该模型在复杂环境中的高灵敏度和稳健性。","MAPL-EMIT 展示了强大的协作，将谷歌的机器学习专长与 NASA JPL 合作伙伴的领域知识相结合。我们共同推进了设施级空间甲烷观测的全部潜力，为全球社区提供必要工具，从而推动在减少温室气体排放方面采取有意义的行动。","我们要感谢在谷歌和NASA喷气推进实验室（JPL）工作的个人，他们开展了这项工作并使发射成为可能，包括（按字母顺序）：Alex Wilson, Anna M. Michalak, Varun Gulshan, Philip G. Brodrick, Andrew K. Thorpe, Christopher V. Arsdale, Burak Ekim, Carl Elkin, Tal Geller, Omry Gillon, Nita Goyal, Mansi Kansal, Roy Nadler, John Platt, Sergei Shames, Bijoy Shetty, Aaron Sonabend, Deepika Sukhija, Shahar Timnat, Maxim Neumann, Anton Raichuk, Frances Reuland, Adam R. Brandt, David R. Thompson, Robert O. Green, Jay Radzinski, Vishal V. Batchu, 以及 Michelangelo Conserva。"],"translationStatus":"translated","bodyOrigin":"source-page","editorial":{"summary":"Google 与 NASA JPL 在 PNAS 发表 MAPL-EMIT。该框架基于 Swin-S 视觉 Transformer，可处理 EMIT 高光谱数据，自动检测和量化甲烷羽流，并估计排放源位置。","background":"甲烷百年尺度增温潜势约为二氧化碳的30倍，并贡献了工业时代以来约25%的人为增温。NASA 的 EMIT 搭载于国际空间站，可利用每个像素记录的数百个光谱波段识别甲烷的化学特征。","viewpoint":"Aioga 判断：MAPL-EMIT 的重点在于把原始卫星高光谱数据转化为可规模化处理的甲烷羽流信息。其编辑价值可能体现在连接全球观测、局地源定位与后续减排行动。","implications":"可能影响：自动化检测、量化和源估计可能提升甲烷点源追踪效率，但不代表卫星观测已解决覆盖范围、空间分辨率与光谱分辨率之间的权衡，实际应用仍需要结合数据条件评估。","nextStep":"后续观察：需要关注 PNAS 论文披露的验证结果、模型在不同地区与观测条件下的表现，以及检测、增强量化和排放源估计如何进入持续更新的全球监测流程。","evidenceRefs":["title","summary","articleBody","source"],"status":"published","aiGenerated":true,"autoApproved":true,"generatedBy":"aioga-editorial:gpt-5.6-sol","reviewedBy":"aioga-editorial-review:gpt-5.6-sol","generatedAt":"2026-09-01T20:24:43.567Z","sourceHash":"5ae4809e1184a1c2","review":{"approved":true,"groundedness":94,"clarity":92,"duplicationRisk":15,"blockingIssues":[],"notes":["“编辑价值可能体现在……”和“可能影响”已明确作为判断或推断表达，没有将观点冒充事实。","“实际应用仍需要结合数据条件评估”属于基于来源中观测权衡因素的谨慎推论，未构成阻断问题。","后续观察内容属于合理的编辑跟踪建议，不是未经来源支持的事实断言。"]},"validation":{"passed":true,"mode":"ai-auto","revisions":0,"checks":["schema","length","source-attribution","editorial-labels","inference-boundary","low-source-overlap","no-html","independent-ai-review"]}},"tags":["行业动态","Google Research：Blog（网页）"],"translations":{"zh-CN":{"title":"Google 与 NASA JPL 发布 MAPL-EMIT 深度学习框架，用卫星高光谱数据绘制全球甲烷排放","summary":"Google 与 NASA JPL 在 PNAS 发表 MAPL-EMIT，一个基于 Swin-S vision transformer 的深度学习框架，可自动化检测、量化甲烷羽流并定位排放源。","category":"行业动态","source":"Google Research：Blog（网页）","aggregationSource":"Google Research：Blog（网页）","pageTitle":"Google 与 NASA JPL 发布 MAPL-EMIT 深度学习框架，用卫星高光谱数据绘制全球甲烷排放 - Aioga AI资讯","description":"Google 与 NASA JPL 在 PNAS 发表 MAPL-EMIT，一个基于 Swin-S vision transformer 的深度学习框架，可自动化检测、量化甲烷羽流并定位排放源。","url":"https://www.aioga.com/news/cmtj3dl5b04raroh9axj6ugai/","articleBody":["谷歌研究院研究工程师Vishal Batchu和研究科学家Michelangelo Conserva。","甲烷分析与羽流定位与EMIT模型是一种深度学习框架，能够自动化全球范围内甲烷羽流的检测、增强量化和源估计，将原始卫星数据转化为可扩展的气候行动。","甲烷：https：//en.wikipedia.org/wiki/甲烷是一种强效温室气体;在100年的时间范围内，其变暖潜力是二氧化碳的30倍：https：//www.ipcc.ch/assessment-report/ar6/。事实上，自工业时代开始以来，甲烷推动了约25%的人为变暖：https：//www.ipcc.ch/assessment-report/ar6/。由于甲烷的大气寿命相对较短，及时减少这些排放为缓解全球气温上升提供了关键的“快速行动”途径。","这一紧迫性体现在全球甲烷承诺：https：//www.globalmethanepledge.org/ 中，已有125多个国家承诺到2030年减少30%的排放。为实现这些目标，我们必须赋能利益相关者追踪废弃物、农业和能源领域的局部点源（仅数十米空间足迹产生的排放）。最具成本效益的策略是减少石油和天然气基础设施、农业设施和垃圾填埋场的排放。","为了在全球范围内追踪这些排放，科学家们越来越依赖基于空间的成像技术。一个典型例子是美国宇航局（NASA）国际空间站上的地表矿物尘埃源调查仪：https：//earth.jpl.nasa.gov/emit/（EMIT）。虽然最初设计用于绘制干旱地区的矿物成分，但NASA喷气推进实验室（JPL）的科学家们利用了EMIT先进的高光谱技术（https：//en.wikipedia.org/wiki/Hyperspectral_imaging 能力来探测甲烷排放。通过记录每个像素数百条不同的光带，研究人员能够“看到”这些原本不可见气体独特的化学指纹。","从太空观察甲烷检测的全球视图。当我们逐渐放大时，MAPL-EMIT 模型会突出显示特定的甲烷羽流，揭示关键细节，例如来源位置。","从太空测量甲烷需要在三个关键因素之间取得平衡：（1）视野（空间覆盖/重访），（2）空间分辨率，以及（3）光谱分辨率。","全球测绘器如 TROPOMI：https://www.tropomi.eu/ 被设计用于通过集成高覆盖范围（约 2,600 公里扫描宽度）、粗空间分辨率（约 5.5 公里 x 3.5 公里）和精细光谱采样（0.1 纳米）来检测背景甲烷浓度的微小变化。","相比之下，点源测绘器如 EMIT 擅长在设施尺度上测量甲烷排放。它们通过将中等覆盖范围（80 公里宽视野）与极高空间分辨率（60 米）和中等光谱分辨率（7.4 纳米光谱采样）结合，实现高信噪比捕捉甲烷的化学特征。","然而，要在全球范围内充分释放这些丰富数据的潜力，还面临额外挑战。地球多样的景观提供了复杂的背景，而一些地表材料可能伪装成甲烷，使得识别较小或较分散的源尤其具有挑战性。为了在 EMIT 团队的基础工作上进一步发展并实现高通量全球测绘，我们与他们合作，应用能够理解场景更广泛视觉上下文的深度学习模型。","这项工作与谷歌在 Google Earth AI：https://ai.google/earth-ai/ 背后的更广泛努力一致，这是我们收集的地理空间模型和数据集，旨在将行星数据转化为可操作的情报。通过大规模将深度学习应用于卫星影像，我们希望用专门工具补充更广泛的行星 AI 项目，用于针对性环境监测。","发现隐形之物。该比较展示了甲烷检测的挑战：标准可见光影像未显示气体，NASA L2B 增强：https://www.earthdata.nasa.gov/data/catalog/lpcloud-emitl2bch4enh-002（基于匹配滤波器）显示噪声信号，但 MAPL-EMIT 模型清晰地将甲烷羽流从背景景观中分离出来。","我们使用端到端视觉变换器架构（Swin-S transformer：https://arxiv.org/abs/2103.14030）构建了 MAPL-EMIT。虽然许多方法是逐像素分析高光谱数据，但 MAPL-EMIT 利用现代计算机视觉技术处理完整的光谱信息及其周围的空间上下文。通过分析气体在景观中的扩散方式，该模型能够更好地区分真正的风吹甲烷羽流（来自特定源的甲烷气体扩散轨迹）和仅仅具有相似光谱特征的地面区域，这在过去常导致甲烷误检。","关键是，这种空间意识使模型能够解开高度复杂的场景。在密集的工业区域，多个相邻设施的排放物经常混合成一个单一的云层。为了理解这些情景，MAPL-EMIT 同时解决三个不同的任务：","解开复杂排放。通过分析空间上下文，MAPL-EMIT 能够同时描绘多重重叠的甲烷羽流的精确形状，并定位其各自的来源（用 X 标记），即使在密集的工业区域也能做到。","基于变换器的模型需要海量数据来学习，但全球范围内包含数百万真实甲烷排放的标注数据集根本不存在。为克服这一问题，我们开发了基于物理的模拟框架。我们创建了 360 万个合成甲烷羽流，并将其直接注入到真实的 EMIT 场景中。通过使用拉格朗日烟羽模型：https://www.nature.com/nature-index/topics/l4/lagrangian-particle-dispersion-modeling-in-atmospheric-studies，该模型模拟了颗粒在空气中的运动和扩散，我们能够重现实际气体排放的混乱和湍流现实。基于这些高度逼真的模拟进行训练，使 MAPL-EMIT 学会在各种大气和地理条件下检测甲烷。这种合成训练方法提供了几个关键优势：","使用合成现实进行训练。由于不存在数百万个带标签的真实甲烷羽流，我们通过将基于物理模拟的羽流（代表不同的排放速率和湍流大气条件）直接注入真实的 EMIT 高光谱场景来训练模型。","在实际卫星数据上的应用表明，MAPL-EMIT 在可扩展排放映射方面显示出强大的潜力。在与 NASA 的黄金标准 L2B 甲烷羽流数据集（https://www.earthdata.nasa.gov/data/catalog/lpcloud-emitl2bch4plm-002）进行基准测试时，该模型捕捉到了 84% 的专家标注羽流，并在约 1100 个 EMIT 数据块中识别出约多 50% 的合理羽流，展示了其从背景噪声中分离微弱信号的能力。更多细节请参见论文：https://www.pnas.org/doi/10.1073/pnas.2612145123。","这种增强的灵敏度还使 MAPL-EMIT 能够可靠地捕捉较弱排放，改进了现有检测极限。该模型在复杂环境中也表现出了稳健性，成功绘制了全球 25 个排放量最高的垃圾填埋场中的 24 个的羽流。","与许多高灵敏度模型一样，假阳性仍然是一个持续的挑战，尤其是在复杂地形中。为帮助缓解这一问题，输出结果与基于物理的羽流置信度（光谱拟合）评分（https://www.sciencedirect.com/science/article/pii/S0034425725002640）配对，根据跨步推理的检测次数进行评估，并使用多种其他属性进行评估，使用户能够根据需要筛选并在捕捉真实羽流能力与假阳性风险之间进行权衡。然而，这并非总是直观的，因此我们还根据这些属性为每个羽流标记“低”或“高”置信度，使用户能够直接使用数据。","追踪持续排放随时间的变化。MAPL-EMIT 甲烷检测的时间序列成功捕捉了来自约旦安曼一处主要垃圾填埋场的羽流，展示了该模型在复杂环境中的高灵敏度和稳健性。","MAPL-EMIT 展示了强大的协作，将谷歌的机器学习专长与 NASA JPL 合作伙伴的领域知识相结合。我们共同推进了设施级空间甲烷观测的全部潜力，为全球社区提供必要工具，从而推动在减少温室气体排放方面采取有意义的行动。","我们要感谢在谷歌和NASA喷气推进实验室（JPL）工作的个人，他们开展了这项工作并使发射成为可能，包括（按字母顺序）：Alex Wilson, Anna M. Michalak, Varun Gulshan, Philip G. Brodrick, Andrew K. Thorpe, Christopher V. Arsdale, Burak Ekim, Carl Elkin, Tal Geller, Omry Gillon, Nita Goyal, Mansi Kansal, Roy Nadler, John Platt, Sergei Shames, Bijoy Shetty, Aaron Sonabend, Deepika Sukhija, Shahar Timnat, Maxim Neumann, Anton Raichuk, Frances Reuland, Adam R. Brandt, David R. Thompson, Robert O. Green, Jay Radzinski, Vishal V. Batchu, 以及 Michelangelo Conserva。"]},"en":{"title":"Google and NASA JPL release MAPL-EMIT deep learning framework to map global methane emissions using satellite hyperspectral data","summary":"Google and NASA JPL published MAPL-EMIT in PNAS, a deep learning framework based on the Swin-S vision transformer, which can automatically detect, quantify methane plumes, and locate emission sources.","category":"Industry","source":"Google Research：Blog（网页）","aggregationSource":"Google Research：Blog（网页）","pageTitle":"Google and NASA JPL release MAPL-EMIT deep learning framework to map global methane emissions using satellite hyperspectral data - Aioga AI News","description":"Google and NASA JPL published MAPL-EMIT in PNAS, a deep learning framework based on the Swin-S vision transformer, which can automatically detect, quantify methane plumes, and loca...","url":"https://www.aioga.com/en/news/cmtj3dl5b04raroh9axj6ugai/","contentTranslated":true,"sourceHash":"351175ff7e97d495","translatedAt":"2026-09-01T20:21:25.439Z"},"ja":{"title":"Google と NASA JPL が MAPL-EMIT 深層学習フレームワークを発表、衛星の高分光データで全球メタン排出量をマッピング","summary":"Google と NASA JPL は PNAS にて MAPL-EMIT を発表した。この深層学習フレームワークは Swin-S ビジョントランスフォーマーに基づき、メタンプルームの自動検出・定量化および排出源の特定を可能にする。","category":"業界動向","source":"Google Research：Blog（网页）","aggregationSource":"Google Research：Blog（网页）","pageTitle":"Google と NASA JPL が MAPL-EMIT 深層学習フレームワークを発表、衛星の高分光データで全球メタン排出量をマッピング - Aioga AIニュース","description":"Google と NASA JPL は PNAS にて MAPL-EMIT を発表した。この深層学習フレームワークは Swin-S ビジョントランスフォーマーに基づき、メタンプルームの自動検出・定量化および排出源の特定を可能にする。","url":"https://www.aioga.com/ja/news/cmtj3dl5b04raroh9axj6ugai/","contentTranslated":true,"sourceHash":"351175ff7e97d495","translatedAt":"2026-09-01T20:21:29.608Z"},"ko":{"title":"Google과 NASA JPL은 MAPL-EMIT 딥러닝 프레임워크를 발표하고, 위성 하이퍼스펙트럼 데이터를 사용해 전 세계 메탄 배출을 시각화했습니다.","summary":"Google과 NASA JPL은 PNAS에 MAPL-EMIT을 발표했습니다. 이는 Swin-S 비전 트랜스포머를 기반으로 한 딥러닝 프레임워크로, 메탄 배출 플룸을 자동으로 감지하고 정량화하며 배출원을 위치 파악할 수 있습니다.","category":"업계 동향","source":"Google Research：Blog（网页）","aggregationSource":"Google Research：Blog（网页）","pageTitle":"Google과 NASA JPL은 MAPL-EMIT 딥러닝 프레임워크를 발표하고, 위성 하이퍼스펙트럼 데이터를 사용해 전 세계 메탄 배출을 시각화했습니다. - Aioga AI 뉴스","description":"Google과 NASA JPL은 PNAS에 MAPL-EMIT을 발표했습니다. 이는 Swin-S 비전 트랜스포머를 기반으로 한 딥러닝 프레임워크로, 메탄 배출 플룸을 자동으로 감지하고 정량화하며 배출원을 위치 파악할 수 있습니다.","url":"https://www.aioga.com/ko/news/cmtj3dl5b04raroh9axj6ugai/","contentTranslated":true,"sourceHash":"351175ff7e97d495","translatedAt":"2026-09-01T20:21:33.712Z"},"es":{"title":"Google y NASA JPL lanzan el marco de aprendizaje profundo MAPL-EMIT para mapear emisiones globales de metano utilizando datos hiperespectrales de satélites","summary":"Google y NASA JPL publicaron en PNAS MAPL-EMIT, un marco de aprendizaje profundo basado en el transformador de visión Swin-S, que permite automatizar la detección, cuantificación de plumas de metano y localización de sus fuentes de emisión.","category":"Industria","source":"Google Research：Blog（网页）","aggregationSource":"Google Research：Blog（网页）","pageTitle":"Google y NASA JPL lanzan el marco de aprendizaje profundo MAPL-EMIT para mapear emisiones globales de metano utilizando datos hiperespectrales de satélites - Aioga Noticias de IA","description":"Google y NASA JPL publicaron en PNAS MAPL-EMIT, un marco de aprendizaje profundo basado en el transformador de visión Swin-S, que permite automatizar la detección, cuantificación d...","url":"https://www.aioga.com/es/news/cmtj3dl5b04raroh9axj6ugai/","contentTranslated":true,"sourceHash":"351175ff7e97d495","translatedAt":"2026-09-01T20:21:37.670Z"},"fr":{"title":"Google et la NASA JPL publient le cadre d'apprentissage profond MAPL-EMIT pour cartographier les émissions mondiales de méthane à partir de données hyperspectrales satellitaires","summary":"Google et la NASA JPL ont publié dans PNAS MAPL-EMIT, un cadre d'apprentissage profond basé sur le vision transformer Swin-S, capable de détecter, quantifier et localiser automatiquement les panaches de méthane et leurs sources d'émission.","category":"Industrie","source":"Google Research：Blog（网页）","aggregationSource":"Google Research：Blog（网页）","pageTitle":"Google et la NASA JPL publient le cadre d'apprentissage profond MAPL-EMIT pour cartographier les émissions mondiales de méthane à partir de données hyperspectrales satellitaires - Aioga Actualités IA","description":"Google et la NASA JPL ont publié dans PNAS MAPL-EMIT, un cadre d'apprentissage profond basé sur le vision transformer Swin-S, capable de détecter, quantifier et localiser automatiq...","url":"https://www.aioga.com/fr/news/cmtj3dl5b04raroh9axj6ugai/","contentTranslated":true,"sourceHash":"351175ff7e97d495","translatedAt":"2026-09-01T20:21:42.464Z"},"de":{"title":"Google und NASA JPL veröffentlichen MAPL-EMIT Deep-Learning-Rahmenwerk zur Kartierung globaler Methanemissionen mit Satelliten-Hyperspektraldaten","summary":"Google und NASA JPL veröffentlichten in PNAS MAPL-EMIT, ein Deep-Learning-Rahmenwerk basierend auf dem Swin-S Vision Transformer, das Methan-Fahnen automatisch erkennt, quantifiziert und die Emissionsquellen lokalisiert.","category":"行业动态","source":"Google Research：Blog（网页）","aggregationSource":"Google Research：Blog（网页）","pageTitle":"Google und NASA JPL veröffentlichen MAPL-EMIT Deep-Learning-Rahmenwerk zur Kartierung globaler Methanemissionen mit Satelliten-Hyperspektraldaten - Aioga KI-News","description":"Google und NASA JPL veröffentlichten in PNAS MAPL-EMIT, ein Deep-Learning-Rahmenwerk basierend auf dem Swin-S Vision Transformer, das Methan-Fahnen automatisch erkennt, quantifizie...","url":"https://www.aioga.com/de/news/cmtj3dl5b04raroh9axj6ugai/","contentTranslated":true,"sourceHash":"351175ff7e97d495","translatedAt":"2026-09-01T20:21:44.667Z"},"pt-BR":{"title":"Google e NASA JPL lançam framework de aprendizado profundo MAPL-EMIT para mapear emissões globais de metano usando dados hiperespectrais de satélite","summary":"Google e NASA JPL publicaram na PNAS o MAPL-EMIT, um framework de aprendizado profundo baseado no transformador de visão Swin-S, capaz de detectar automaticamente, quantificar mangueiras de metano e localizar fontes de emissão.","category":"行业动态","source":"Google Research：Blog（网页）","aggregationSource":"Google Research：Blog（网页）","pageTitle":"Google e NASA JPL lançam framework de aprendizado profundo MAPL-EMIT para mapear emissões globais de metano usando dados hiperespectrais de satélite - Aioga Notícias de IA","description":"Google e NASA JPL publicaram na PNAS o MAPL-EMIT, um framework de aprendizado profundo baseado no transformador de visão Swin-S, capaz de detectar automaticamente, quantificar mang...","url":"https://www.aioga.com/pt-BR/news/cmtj3dl5b04raroh9axj6ugai/","contentTranslated":true,"sourceHash":"351175ff7e97d495","translatedAt":"2026-09-01T20:21:51.311Z"},"ru":{"title":"Google и NASA JPL выпустили фреймворк глубокого обучения MAPL-EMIT для отображения глобальных выбросов метана с использованием гиперспектральных данных спутников","summary":"Google и NASA JPL опубликовали в PNAS MAPL-EMIT, фреймворк глубокого обучения на основе Swin-S vision transformer, который может автоматически обнаруживать и количественно оценивать plumes метана, а также определять источники выбросов.","category":"行业动态","source":"Google Research：Blog（网页）","aggregationSource":"Google Research：Blog（网页）","pageTitle":"Google и NASA JPL выпустили фреймворк глубокого обучения MAPL-EMIT для отображения глобальных выбросов метана с использованием гиперспектральных данных спутников - Aioga Новости ИИ","description":"Google и NASA JPL опубликовали в PNAS MAPL-EMIT, фреймворк глубокого обучения на основе Swin-S vision transformer, который может автоматически обнаруживать и количественно оцениват...","url":"https://www.aioga.com/ru/news/cmtj3dl5b04raroh9axj6ugai/","contentTranslated":true,"sourceHash":"351175ff7e97d495","translatedAt":"2026-09-01T20:21:49.961Z"},"ar":{"title":"جوجل و ناسا JPL يصدران إطار التعلم العميق MAPL-EMIT لرسم انبعاثات الميثان العالمية باستخدام بيانات الأقمار الصناعية الطيفية العالية","summary":"نشرت جوجل و ناسا JPL في PNAS إطار MAPL-EMIT، وهو إطار تعلم عميق قائم على Swin-S vision transformer، يمكنه الكشف الآلي عن تدفقات الميثان وقياسها وتحديد مصادر الانبعاث.","category":"行业动态","source":"Google Research：Blog（网页）","aggregationSource":"Google Research：Blog（网页）","pageTitle":"جوجل و ناسا JPL يصدران إطار التعلم العميق MAPL-EMIT لرسم انبعاثات الميثان العالمية باستخدام بيانات الأقمار الصناعية الطيفية العالية - Aioga أخبار الذكاء الاصطناعي","description":"نشرت جوجل و ناسا JPL في PNAS إطار MAPL-EMIT، وهو إطار تعلم عميق قائم على Swin-S vision transformer، يمكنه الكشف الآلي عن تدفقات الميثان وقياسها وتحديد مصادر الانبعاث.","url":"https://www.aioga.com/ar/news/cmtj3dl5b04raroh9axj6ugai/","contentTranslated":true,"sourceHash":"351175ff7e97d495","translatedAt":"2026-09-01T20:21:55.311Z"},"hi":{"title":"गूगल और NASA JPL ने MAPL-EMIT डीप लर्निंग फ्रेमवर्क जारी किया, जो उपग्रह के उच्च-स्पेक्ट्रम डेटा से वैश्विक मीथेन उत्सर्जन को मैप करता है","summary":"गूगल और NASA JPL ने PNAS में MAPL-EMIT प्रकाशित किया, एक स्विन-S विज़न ट्रांसफॉर्मर आधारित डीप लर्निंग फ्रेमवर्क, जो मीथेन प्लूम का स्वत: पता लगाने, मापने और उत्सर्जन स्रोत का स्थान निर्धारित करने में सक्षम है।","category":"行业动态","source":"Google Research：Blog（网页）","aggregationSource":"Google Research：Blog（网页）","pageTitle":"गूगल और NASA JPL ने MAPL-EMIT डीप लर्निंग फ्रेमवर्क जारी किया, जो उपग्रह के उच्च-स्पेक्ट्रम डेटा से वैश्विक मीथेन उत्सर्जन को मैप करता है - Aioga AI समाचार","description":"गूगल और NASA JPL ने PNAS में MAPL-EMIT प्रकाशित किया, एक स्विन-S विज़न ट्रांसफॉर्मर आधारित डीप लर्निंग फ्रेमवर्क, जो मीथेन प्लूम का स्वत: पता लगाने, मापने और उत्सर्जन स्रोत का स्था...","url":"https://www.aioga.com/hi/news/cmtj3dl5b04raroh9axj6ugai/","contentTranslated":true,"sourceHash":"351175ff7e97d495","translatedAt":"2026-09-01T20:21:56.531Z"},"it":{"title":"Google e NASA JPL rilasciano il framework di deep learning MAPL-EMIT per mappare le emissioni globali di metano con dati satellitari iperspettrali","summary":"Google e NASA JPL hanno pubblicato su PNAS MAPL-EMIT, un framework di deep learning basato su Swin-S vision transformer, in grado di rilevare, quantificare automaticamente i flussi di metano e identificare le fonti di emissione.","category":"行业动态","source":"Google Research：Blog（网页）","aggregationSource":"Google Research：Blog（网页）","pageTitle":"Google e NASA JPL rilasciano il framework di deep learning MAPL-EMIT per mappare le emissioni globali di metano con dati satellitari iperspettrali - Aioga Notizie IA","description":"Google e NASA JPL hanno pubblicato su PNAS MAPL-EMIT, un framework di deep learning basato su Swin-S vision transformer, in grado di rilevare, quantificare automaticamente i flussi...","url":"https://www.aioga.com/it/news/cmtj3dl5b04raroh9axj6ugai/","contentTranslated":true,"sourceHash":"351175ff7e97d495","translatedAt":"2026-09-01T20:22:01.191Z"},"nl":{"title":"Google en NASA JPL publiceren het diepleerframework MAPL-EMIT om mondiale methaanuitstoot in kaart te brengen met hyperspectrale satellietgegevens","summary":"Google en NASA JPL publiceerden in PNAS MAPL-EMIT, een diepleerframework gebaseerd op de Swin-S vision transformer, dat automatisch methaanpluimen kan detecteren, kwantificeren en de bron van emissies kan lokaliseren.","category":"行业动态","source":"Google Research：Blog（网页）","aggregationSource":"Google Research：Blog（网页）","pageTitle":"Google en NASA JPL publiceren het diepleerframework MAPL-EMIT om mondiale methaanuitstoot in kaart te brengen met hyperspectrale satellietgegevens - Aioga AI-nieuws","description":"Google en NASA JPL publiceerden in PNAS MAPL-EMIT, een diepleerframework gebaseerd op de Swin-S vision transformer, dat automatisch methaanpluimen kan detecteren, kwantificeren en...","url":"https://www.aioga.com/nl/news/cmtj3dl5b04raroh9axj6ugai/","contentTranslated":true,"sourceHash":"351175ff7e97d495","translatedAt":"2026-09-01T20:22:00.526Z"},"tr":{"title":"Google ve NASA JPL, MAPL-EMIT derin öğrenme çerçevesini yayınladı; uydu hiperspektral verilerini kullanarak dünya genelindeki metan emisyonlarını haritalıyor","summary":"Google ve NASA JPL, PNAS’ta MAPL-EMIT’i yayınladı; Swin-S vision transformer’a dayalı bu derin öğrenme çerçevesi, metan bulutlarını otomatik olarak tespit edebiliyor, miktarını ölçebiliyor ve emisyon kaynaklarını belirleyebiliyor.","category":"行业动态","source":"Google Research：Blog（网页）","aggregationSource":"Google Research：Blog（网页）","pageTitle":"Google ve NASA JPL, MAPL-EMIT derin öğrenme çerçevesini yayınladı; uydu hiperspektral verilerini kullanarak dünya genelindeki metan emisyonlarını haritalıyor - Aioga AI Haberleri","description":"Google ve NASA JPL, PNAS’ta MAPL-EMIT’i yayınladı; Swin-S vision transformer’a dayalı bu derin öğrenme çerçevesi, metan bulutlarını otomatik olarak tespit edebiliyor, miktarını ölç...","url":"https://www.aioga.com/tr/news/cmtj3dl5b04raroh9axj6ugai/","contentTranslated":true,"sourceHash":"351175ff7e97d495","translatedAt":"2026-09-01T20:22:06.353Z"},"vi":{"title":"Google và NASA JPL ra mắt khung học sâu MAPL-EMIT, sử dụng dữ liệu phổ cao từ vệ tinh để vẽ phát thải khí methane toàn cầu","summary":"Google và NASA JPL công bố trên PNAS khung học sâu MAPL-EMIT, dựa trên Swin-S vision transformer, có khả năng tự động phát hiện, lượng hóa luồng khí methane và xác định nguồn phát thải.","category":"行业动态","source":"Google Research：Blog（网页）","aggregationSource":"Google Research：Blog（网页）","pageTitle":"Google và NASA JPL ra mắt khung học sâu MAPL-EMIT, sử dụng dữ liệu phổ cao từ vệ tinh để vẽ phát thải khí methane toàn cầu - Tin tức AI Aioga","description":"Google và NASA JPL công bố trên PNAS khung học sâu MAPL-EMIT, dựa trên Swin-S vision transformer, có khả năng tự động phát hiện, lượng hóa luồng khí methane và xác định nguồn phát...","url":"https://www.aioga.com/vi/news/cmtj3dl5b04raroh9axj6ugai/","contentTranslated":true,"sourceHash":"351175ff7e97d495","translatedAt":"2026-09-01T20:22:04.817Z"},"id":{"title":"Google dan NASA JPL merilis kerangka kerja pembelajaran mendalam MAPL-EMIT untuk memetakan emisi metana global menggunakan data hiperspektral satelit","summary":"Google dan NASA JPL menerbitkan di PNAS MAPL-EMIT, sebuah kerangka kerja pembelajaran mendalam berbasis Swin-S vision transformer, yang dapat secara otomatis mendeteksi, mengukur aliran metana, dan menentukan sumber emisi.","category":"行业动态","source":"Google Research：Blog（网页）","aggregationSource":"Google Research：Blog（网页）","pageTitle":"Google dan NASA JPL merilis kerangka kerja pembelajaran mendalam MAPL-EMIT untuk memetakan emisi metana global menggunakan data hiperspektral satelit - Berita AI Aioga","description":"Google dan NASA JPL menerbitkan di PNAS MAPL-EMIT, sebuah kerangka kerja pembelajaran mendalam berbasis Swin-S vision transformer, yang dapat secara otomatis mendeteksi, mengukur a...","url":"https://www.aioga.com/id/news/cmtj3dl5b04raroh9axj6ugai/","contentTranslated":true,"sourceHash":"351175ff7e97d495","translatedAt":"2026-09-01T20:22:10.061Z"},"th":{"title":"Google และ NASA JPL เปิดตัวกรอบการเรียนรู้เชิงลึก MAPL-EMIT ใช้ข้อมูลสเปกตรัมสูงจากดาวเทียมวางแผนการปล่อยมีเทนทั่วโลก","summary":"Google และ NASA JPL เผยแพร่ MAPL-EMIT ใน PNAS เป็นกรอบการเรียนรู้เชิงลึกที่อิงกับ Swin-S vision transformer สามารถตรวจจับ คำนวณปริมาณเส้นทางของมีเทน และระบุตำแหน่งแหล่งปล่อยโดยอัตโนมัติ","category":"行业动态","source":"Google Research：Blog（网页）","aggregationSource":"Google Research：Blog（网页）","pageTitle":"Google และ NASA JPL เปิดตัวกรอบการเรียนรู้เชิงลึก MAPL-EMIT ใช้ข้อมูลสเปกตรัมสูงจากดาวเทียมวางแผนการปล่อยมีเทนทั่วโลก - ข่าว AI Aioga","description":"Google และ NASA JPL เผยแพร่ MAPL-EMIT ใน PNAS เป็นกรอบการเรียนรู้เชิงลึกที่อิงกับ Swin-S vision transformer สามารถตรวจจับ คำนวณปริมาณเส้นทางของมีเทน และระบุตำแหน่งแหล่งปล่อยโดยอัตโ...","url":"https://www.aioga.com/th/news/cmtj3dl5b04raroh9axj6ugai/","contentTranslated":true,"sourceHash":"351175ff7e97d495","translatedAt":"2026-09-01T20:22:12.785Z"},"pl":{"title":"Google i NASA JPL wydają framework głębokiego uczenia MAPL-EMIT, używając danych hiperspektralnych satelitów do mapowania globalnej emisji metanu","summary":"Google i NASA JPL opublikowali w PNAS MAPL-EMIT, framework głębokiego uczenia oparty na Swin-S vision transformer, który może automatycznie wykrywać, ilościowo określać strumienie metanu i lokalizować źródła emisji.","category":"行业动态","source":"Google Research：Blog（网页）","aggregationSource":"Google Research：Blog（网页）","pageTitle":"Google i NASA JPL wydają framework głębokiego uczenia MAPL-EMIT, używając danych hiperspektralnych satelitów do mapowania globalnej emisji metanu - Aioga Wiadomości AI","description":"Google i NASA JPL opublikowali w PNAS MAPL-EMIT, framework głębokiego uczenia oparty na Swin-S vision transformer, który może automatycznie wykrywać, ilościowo określać strumienie...","url":"https://www.aioga.com/pl/news/cmtj3dl5b04raroh9axj6ugai/","contentTranslated":true,"sourceHash":"351175ff7e97d495","translatedAt":"2026-09-01T20:22:16.960Z"}},"evidenceTier":"verified-news","reviewStatus":"automated-ingest","indexable":true,"editorialCover":"/page-visuals/topic-timeline.png"}}