Search

Recognizing and classifying natural or artificial geo-objects under complex geo-scenes using remotely sensed data remains a significant challenge due to the heterogeneity in their spatial distribution and sampling bias. In this study, we propose a deep learning method of surface complexity analysis based on multiscale entropy. This method can be used to reduce sampling bias and preserve entropy-based invariance in learning for the semantic segmentation of land use and land cover (LULC) images. Our quantitative models effectively identified and extracted local surface complexity scores, demonstrating their broad applicability. We tested our method using the Gaofen-2 image dataset in mainland China and accurately estimated multiscale complexity. A downstream evaluation revealed that our approach achieved similar or better performance compared to several representative state-of-the-art deep learning methods. This highlights the innovative and significant contribution of our entropy-based complexity analysis and its applicability in improving LULC semantic segmentations through optimal stratified sampling and constrained optimization, which can also potentially be used to enhance semantic segmentation under complex geo-scenes using other machine learning methods. [ABSTRACT FROM AUTHOR]

In recent years, the ever-increasing charging demand of electric vehicles (EVs) imposes challenges on both power supply security and reliability in the distribution system. In this paper, an EV accommodation capability evaluation model of a distribution system, with high penetrations of flexible resources, is established. Firstly, according to the actual classifications of EVs and transportation rules, a Monte Carlo simulation is used to simulate the charging behaviors of EVs so as to obtain the relevant parameters of EV charging. Then, a coordinated charging optimization model for various types of EVs is proposed based on the charging characteristics of EVs. The presented model comprises a mixed-integer linear programming problem and a constrained optimization problem which are respectively solved by CPLEX (the Simplex method implemented in the °C programming language) and the particle swarm optimization (PSO) algorithm. Last of all, a real-life distribution system in the coastal areas of China is served for demonstrating the feasibility and efficiency of the proposed approach. Moreover, the impacts of flexible resources, distribution network zoning rules, and EV growth on the EV accommodation capability of a distribution system are also discussed. [ABSTRACT FROM AUTHOR]