ABSTRACT

Recent improvements in the spatial, temporal, and spectral resolution of satellite images necessitate (semi-)automated classification and information extraction approaches. Therefore, we developed an integrated fuzzy object-based image analysis and deep learning (FOBIA-DL) approach for monitoring the land use/cover (LULC) and respective changes and compared it to three machine learning (ML) algorithms, namely the support vector machine (SVM), random forest (RF), and classification and regression tree (CART). We investigated LULC impacts on drought by analyzing Landsat satellite images from 1990 to 2020 for the Urmia Lake area in northern Iran. In the FOBIA-DL approach, following the initial segmentation steps, object features were identified for each LULC class. We then derived their respective attributes using fuzzy membership functions and deep convolutional neural networks (DCNNs), a deep learning method. The Fuzzy Synthetic Evaluation and Dempster-Shafer Theory (FSE-DST) also applied to validate and carryout the spatial uncertainties. Our results indicate that the FOBIA-DL, with an accuracy of 90.1% to 96.4% and a spatial certainty of 0.93 to 0.97, outperformed the other approaches, closely followed by the SVM. Our results also showed that the integration of Fuzzy-OBIA and DCNNs could improve the strength and robustness of the OBIA’s decision rules, while the FSE-DST approach notably improved the spatial accuracy of the object-based classification maps. While object-based image analysis (OBIA) is already considered a paradigm shift in GIScience, the integration of OBIA with fuzzy and deep learning creates more flexibility and robust OBIA decision rules for image analysis and classification. This research integrated popular data-driven approaches and developed a novel methodology for image classification and spatial accuracy assessment. From the environmental perspective, the results of this research support lake restoration initiatives by decision-makers and authorities in applications such as drought mitigation, land use management and precision agriculture programs.

摘要

卫星图像空间、时间和光谱分辨率的最新改进需要（半）自动分类和信息提取方法。因此，我们开发了一种集成的基于模糊对象的图像分析和深度学习 (FOBIA-DL) 方法来监测土地利用/覆盖 (LULC) 和各自的变化，并将其与三种机器学习 (ML) 算法进行比较，即支持向量机器 (SVM)、随机森林 (RF) 以及分类和回归树 (CART)。我们通过分析 1990 年至 2020 年伊朗北部乌尔米亚湖地区的 Landsat 卫星图像，研究了 LULC 对干旱的影响。在 FOBIA-DL 方法中，按照初始分割步骤，为每个 LULC 类识别对象特征。然后，我们使用模糊隶属函数和深度卷积神经网络 (DCNN)（一种深度学习方法）推导出它们各自的属性。模糊综合评估和 Dempster-Shafer 理论 (FSE-DST) 也应用于验证和执行空间不确定性。我们的结果表明，FOBIA-DL 的精度为 90.1% 至 96.4%，空间确定性为 0.93 至 0.97，优于其他方法，紧随其后的是 SVM。我们的结果还表明，Fuzzy-OBIA 和 DCNN 的集成可以提高 OBIA 决策规则的强度和鲁棒性，而 FSE-DST 方法显着提高了基于对象的分类图的空间精度。虽然基于对象的图像分析 (OBIA) 已经被认为是 GIScience 的范式转变，OBIA 与模糊和深度学习的集成为图像分析和分类创造了更大的灵活性和鲁棒性的 OBIA 决策规则。这项研究整合了流行的数据驱动方法，并开发了一种用于图像分类和空间精度评估的新方法。从环境角度来看，这项研究的结果支持决策者和当局在干旱缓解、土地利用管理和精准农业计划等应用中的湖泊恢复计划。