Abstract
Crop classification maps are fundamental data for global change research, regional agricultural regulation, fine production, and insurance services. The key to crop classification is samples, but it is very time-consuming in annual field sampling. Therefore, how to use historical samples in crop classification for future years at a lower cost is a research hotspot. By constructing the spectral feature vector of each historical sample in the historical year and its neighboring pixels in the target year, we produced new samples and classified them in the target year. Specifically, based on environmental similarity, we first calculated the similarities of every two pixels between each historical year and target year and took neighboring pixels with the highest local similarity as potential samples. Then, cluster analysis was performed on those potential samples of the same crop, and the class with more pixels is selected as newly generated samples for classification of the target year. The experiment in Heilongjiang province, China showed that this method can generate new samples with the uniform spatial distribution and that the proportion of various crops is consistent with field data in historical years. The overall accuracy of the target year by the newly generated sample and the real sample is 61.57 and 80.58%, respectively. The spatial pattern of maps obtained by two models is basically the same, and the classification based on the newly generated samples identified rice better. For areas with majority fields having no rotation, this method overcomes the problem of insufficient samples caused by difficulties in visual interpretation and high cost on field sampling, effectively improves the utilization rate of historical samples, and provides a new idea for crop mapping in areas lacking field samples of the target year.
Highlights
Large-scale crop mapping is fine detection of land use, and timely and accurate mapping results are basic data for food production prediction, global change research, agricultural insurance evaluation, production process supervision, and adjustment of supply and demand structure (Hao et al, 2015; Huang et al, 2015; Arshad et al, 2018; Liu Z. et al, 2018; Liu et al, 2021; You et al, 2021)
Crop mapping mostly adopts a supervised classification strategy (Yang et al, 2019), which is mainly based on spectral features (Xu L. et al, 2019), spatial patterns (Ren et al, 2020; Zhang et al, 2020), and temporal changes (Arias et al, 2020) of real samples to train crop a classification model, and the classification is conducted by comparing the similarity of series features of unknown pixels or objects with the trained model
Feature vectors constructed by NIR, normalized difference vegetation index (NDVI), and NDWI were selected as the basis for similarity calculation in this study
Summary
Large-scale crop mapping is fine detection of land use, and timely and accurate mapping results are basic data for food production prediction, global change research, agricultural insurance evaluation, production process supervision, and adjustment of supply and demand structure (Hao et al, 2015; Huang et al, 2015; Arshad et al, 2018; Liu Z. et al, 2018; Liu et al, 2021; You et al, 2021). Crop mapping mostly adopts a supervised classification strategy (Yang et al, 2019), which is mainly based on spectral features (Xu L. et al, 2019), spatial patterns (such as shape and texture) (Ren et al, 2020; Zhang et al, 2020), and temporal changes (Arias et al, 2020) of real samples to train crop a classification model, and the classification is conducted by comparing the similarity of series features of unknown pixels or objects with the trained model. This strategy requires a large number of training samples to construct a classification model. We can mention three: the first one is to reuse the spectral characteristics of historical samples for classification; the second one is to transfer a model trained on historical samples for classification; and the third one is to generate new samples for classification
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
