arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.15512cs.LGcs.AIcs.CV
收藏

提升地球观测中缺失传感器的模型预测鲁棒性

Increasing the Robustness of Model Predictions to Missing Sensors in Earth Observation

University of Kaiserslautern-Landau, Kaiserslautern, Germany(凯撒斯劳滕-兰道大学,凯撒斯劳滕,德国);German Research Center for Artificial Intelligence, Kaiserslautern, Germany(德国人工智能研究中心,凯撒斯劳滕,德国)

Francisco Mena, Diego Arenas, Andreas Dengel

AI总结:

本文提出两种新方法ISensD和ESensI,通过实验验证其在多传感器时间序列地球观测数据中提升模型对缺失传感器的鲁棒性。

摘要:

多传感器机器学习模型用于地球观测旨在通过整合不同来源的数据提高预测准确性。然而,缺失数据的存在构成了重大挑战,尤其是非持久传感器可能受外部因素影响。现有文献探讨了时间dropout和传感器不变模型等策略以解决缺失数据的泛化问题。受这些工作启发,我们研究了两种针对多传感器场景的新型方法,即输入传感器dropout(ISensD)和集合传感器不变(ESensI)。通过在三个多传感器时间序列地球观测数据集上的实验,我们证明这些方法有效提高了模型对缺失传感器的鲁棒性。特别是,我们关注当传感器缺失在不同层次时模型的预测性能下降情况。我们发现集合多传感器模型对传感器缺乏最具有鲁棒性。此外,ISensD中的传感器dropout组件显示出有希望的鲁棒性结果。

英文摘要:

Multi-sensor ML models for EO aim to enhance prediction accuracy by integrating data from various sources. However, the presence of missing data poses a significant challenge, particularly in non-persistent sensors that can be affected by external factors. Existing literature has explored strategies like temporal dropout and sensor-invariant models to address the generalization to missing data issues. Inspired by these works, we study two novel methods tailored for multi-sensor scenarios, namely Input Sensor Dropout (ISensD) and Ensemble Sensor Invariant (ESensI). Through experimentation on three multi-sensor temporal EO datasets, we demonstrate that these methods effectively increase the robustness of model predictions to missing sensors. Particularly, we focus on how the predictive performance of models drops when sensors are missing at different levels. We observe that ensemble multi-sensor models are the most robust to the lack of sensors. In addition, the sensor dropout component in ISensD shows promising robustness results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑