The search for ephemeral liquid water on Mars is an ongoing activity. After the recession of the seasonal polar ice cap on Mars, small water ice patches may be left behind in shady places due to the low thermal conductivity of the Martian surface and atmosphere. During late spring and early summer, these patches may be exposed to direct sunlight and warm up rapidly enough for the liquid phase to emerge. To see the spatial and temporal occurrence of such ice patches, optical images should be searched for and checked. Previously a manual image analysis was conducted on 110 images from the southern hemisphere, captured by the High Resolution Imaging Science Experiment (HiRISE) camera onboard the Mars Reconnaissance Orbiter space mission. Out of these, 37 images were identified with smaller ice patches, which were distinguishable by their brightness, colour and strong connection to local topographic shading. In this study, a convolutional neural network (CNN) is applied to find further images with potential water ice patches in the latitude band between -40{\deg} and -60{\deg}, where the seasonal retreat of the polar ice cap happens. Previously analysed HiRISE images are used to train the model, each was split into hundreds of pieces, expanding the training dataset to 6240 images. A test run conducted on 38 new HiRISE images indicates that the program can generally recognise small bright patches, however further training might be needed for more precise predictions.Using a CNN model may make it realistic to analyse all available surface images, aiding us in selecting areas for further investigation.

翻译：火星上是否存在短暂液态水是一个持续探索的问题。随着火星季节性极地冰盖消融，由于火星表面和大气的低热导率，阴影区域可能残留小型水冰斑块。在春末夏初，这些斑块可能直接暴露于阳光并迅速升温，从而形成液态水。为了观测此类冰斑的时空分布，需要搜索并核查光学图像。此前，研究人员对火星勘测轨道飞行器（Mars Reconnaissance Orbiter）搭载的高分辨率成像科学实验（HiRISE）相机在南半球拍摄的110张图像进行了人工分析。其中，37张图像被确认存在小型冰斑，这些冰斑可通过其亮度、颜色及与局部地形阴影的强关联性进行识别。本研究采用卷积神经网络（CNN）在纬度-40°至-60°（极地冰盖季节性退缩区域）范围内寻找可能含有水冰斑的更多图像。利用此前分析的HiRISE图像训练模型，每张图像被分割为数百个子图，将训练数据集扩展至6240张图像。对38张新HiRISE图像的测试运行表明，该程序可初步识别小型亮斑，但需进一步训练以提高预测精度。采用CNN模型可能使分析全部可用表面图像成为现实，从而辅助选定重点探测区域。