Abstract
Nowadays, in the field of data mining, time series data analysis is a very important and challenging subject. This is especially true for time series remote sensing classification. The classification of remote sensing images is an important source of information for land resource planning and management, rational development, and protection. Many experts and scholars have proposed various methods to classify time series data, but when these methods are applied to real remote sensing time series data, there are some deficiencies in classification accuracy. Based on previous experience and the processing methods of time series in other fields, we propose a neural network model based on a self-attention mechanism and time sequence enhancement to classify real remote sensing time series data. The model is mainly divided into five parts: (1) memory feature extraction in subsequence blocks; (2) self-attention layer among blocks; (3) time sequence enhancement; (4) spectral sequence relationship extraction; and (5) a simplified ResNet neural network. The model can simultaneously consider the three characteristics of time series local information, global information, and spectral series relationship information to realize the classification of remote sensing time series. Good experimental results have been obtained by using our model.
Highlights
In recent years, the scale and length of time series data have exploded
In our proposed neural network model, we mainly considered four kinds of features of remote sensing time series data, including the local intra-block memory feature, the inter-block correlation feature, the time sequence importance feature, and the spectral sequence correlation feature
Differentmodels models show classification ofareas someinareas in the study area. (a) OUR. Whether it is on a standard dataset or a dataset of our choice, we can come to the conclusion that the combination of the self-attention. Whether it is on a standard dataset ormechanism a datasetand of the ourcorrelation choice, among we can come multiple bands is beneficial to the time series classification of remote sensing data
Summary
People often come into contact with time series data in their daily lives. In today’s era of big data and artificial intelligence, people are increasingly relying on hidden information mined from time series data. People use this information to benefit their lives. The current quality of time series data processing will directly affect our quality of life. Time series data analysis in the field of remote sensing affects personal lives and productivity—it affects the country’s land management, planning guidelines, and policies. The processing of remote sensing time series has become important
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
