The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.
The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.
Patent No.:
Date of Patent:
Apr. 21, 2025
Filed:
Sep. 29, 2024
East China Jiaotong University, Nanchang, CN;
Lan Song, Nanchang, CN;
East China Jiaotong University, Nanchang, CN;
Abstract
A method for predicting remote sensing image time series based on reservoir computing utilizes temporal spectral information of remote sensing images to study prediction methods for high-dimensional short-term sequences. Based on the theoretical model of a nonlinear dynamical system and using the spatiotemporal transformation equation and its conjugate equation, a multi-layer reservoir computing model is constructed to achieve multi-step prediction on a time dimension. Only a small number of short-term samples are required to predict dynamic temporal information. Compared with the traditional neural network training process, the method is low-cost training. Different from traditional reservoir computing, the method converts the observed high-dimensional data into reservoir computing and uses intrinsic dynamics of the observation/target system to analyze remote sensing time series data. With only a few samples, by learning the spatiotemporal transformation equation, effective prediction results can be generated and applied to feature processing of remote sensing images with small samples.