ABSTRACT

Coal is a principal source of energy and the combustion of coal supplies around one-third of the global electricity generation. Coal mines are also an important source of CH₄ emissions, the second most important greenhouse gas. Monitoring CH₄ emissions caused by coal mining using earth observation will require the exact location of coal mines. This paper aims to determine surface coal mines from satellite images through deep learning techniques by treating them as a land use/land cover classification task. This is achieved using Convolutional Neural Networks (CNN) that has proven to be capable of complex land use/land cover classification tasks. With a list of known coal mine locations from various countries, a training dataset of “Coal Mine” and “No Coal Mine” image patches is prepared using Sentinel-2 satellite images with 13 spectral bands. Various pre-trained CNN network architectures (VGG, ResNet, DenseNet) are trained and validated with our prepared coal mine dataset of 3500 “Coal Mine” and 3000 “No Coal Mine” image patches. After several experiments with the VGG network combined with transfer learning is found to be an optimal model for this task. Classification accuracy of 98% has been achieved for the validation dataset of the pre-trained VGG architecture. The model produces more than 95% overall accuracy when tested on unseen satellite images from different countries outside the training dataset and evaluated against visual classification.

摘要

煤炭是主要的能源，煤炭的燃烧约占全球发电量的三分之一。煤矿还是CH ₄排放的重要来源，CH ₄排放是第二重要的温室气体。监控CH ₄使用对地观测法开采煤矿造成的排放将要求煤矿的确切位置。本文旨在通过深度学习技术，通过将卫星图像视为土地使用/土地覆盖分类任务，从卫星图像中确定地表煤矿。这是使用卷积神经网络（CNN）实现的，该网络已被证明能够完成复杂的土地利用/土地覆盖分类任务。利用来自不同国家的已知煤矿位置列表，使用具有13个光谱带的Sentinel-2卫星图像准备了“煤矿”和“无煤矿”图像补丁的训练数据集。使用我们准备的3500个“煤矿”和3000个“无煤矿”图像补丁的煤矿数据集，对各种预先训练的CNN网络体系结构（VGG，ResNet，DenseNet）进行了培训和验证。在将VGG网络与转移学习相结合进行多次实验后，发现它是完成此任务的最佳模型。对于预训练的VGG体系结构的验证数据集，已达到98％的分类精度。当对来自训练数据集以外的不同国家的看不见的卫星图像进行测试并根据视觉分类进行评估时，该模型可产生95％以上的总体准确性。