SSU-LSF:面向Mamba SSM的机器遗忘框架
Get the story
2026年10月5日,arXiv Machine Learning Theory(一手来源)发表论文,提出SSU-LSF(State-Space Unlearning for Land Surface Forecasting,状态空间遗忘框架)。该框架据称为首个面向地球科学Mamba型状态空间模型(SSM)的机器遗忘框架,目标是消除由灌溉激增、坝调度变化、传感器重校准等非平稳混淆因素造成的长期偏差,涉及NDVI、LST与作物物候预测任务。目前公开信息仅包含该论文摘要层面的方法介绍,尚无实验细节、代码发布或第三方验证的后续报道。
Generated from reports · updated 21 hr ago
Timeline
Follow the coverage from different angles.
- arXiv · Machine Learning TheorySSU-LSF:面向地表预测中非平稳偏差的 state-space 机器遗忘框架
论文提出 SSU-LSF(State-Space Unlearning for Land Surface Forecasting),首个面向地球科学 Mamba 型 SSM 的机器遗忘框架,用于消除灌溉激增、坝调度变化、传感器重校准等非平稳混淆对 NDVI、LST 与作物物候预测的长期偏差。
Heat trend
Current heat 6·Comparable peak 10(Oct 5)·Comparable change over 24 hours –
The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.