HiPredict 用机器学习修复 HiRISE 火星相机失效的 RED4 通道
HiPredict: Predicting the missing HiRISE RED4 spectral channel with machine learning
火星相机的探测器坏了，团队用 U-Net 从其他通道把丢的波段补回来，误差 1.1% 比老方法 3.1% 好不少，还开源了。
MRO 探测器上的 HiRISE 相机以 25–30 cm/像素分辨率拍摄火星，其中心探测器 RED4 自 2023 年起间歇性故障，使彩色成像能力减半。HiPredict 采用 U-Net 架构，从 IR10、BG12 通道、相邻红通道观测和采集元数据重建 RED4，训练数据包含 81,717 个样本（13,625 次观测）。在 23,348 个测试样本上，HiPredict 的归一化平均绝对误差为 1.1%，明显优于原有线性缩放方法 SYN4 的 3.1%。重建结果能更好呈现冰陨石坑、脊线地层和氯化物沉积等特征，该工具已开源。
HiPredict: Predicting the missing HiRISE RED4 spectral channel with machine learning
The High Resolution Imaging Science Experiment (HiRISE) onboard the Mars Reconnaissance Orbiter (MRO) acquires imagery of Mars at 25--30 cm/pixel, supporting studies of martian geology, climate history, and landing-site characterization. Its 14-detector focal plane assembly includes several overlapping detectors that enable the acquisition of three-channel colour-infrared images, which are important for identifying compositional variations and studying active surface processes. In 2023, a detector in the center of the focal plane assembly (RED4) began failing intermittently, creating a gap in acquired imagery and reducing the instrument's colour-imaging capability by half. The HiRISE processing pipeline provides a synthetic red (SYN4) channel obtained by linearly scaling the co-located infrared (IR10) channel. However, this approach cannot capture observed non-linear relationships between the colour channels, limiting its accuracy and applicability. Here, we present HiPredict, a machine-learning framework that reconstructs RED4 from co-located IR10 and blue-green (BG12) imagery, neighbouring red-channel observations, and acquisition metadata. The model employs a U-Net architecture to learn non-linear spatiotemporal-spectral relationships between these inputs and is trained on 81,717 training samples, representing 13,625 observations. Evaluated on 23,348 test samples, representing 3,892 pre-failure observations, HiPredict reconstructs RED4 with a Normalised Mean Absolute Error of 1.1%, substantially outperforming SYN4 (3.1%). The reconstructed products improve colour image recovery and more closely represent features of interest such as icy craters, stratigraphy exposed along ridge crests and chloride deposits. We release HiPredict as an open software tool. This work demonstrates the potential of machine learning to mitigate data loss as planetary missions age and naturally degrade.
