A precise spatiotemporal fusion crop classification framework based on parcels

Abstract The precise extraction of crop type information on agricultural land supports applications such as agricultural information statistics and planning. It is also a crucial foundation for improving agricultural production efficiency and promoting agricultural informatization. In smallholder ag...

Full description

Saved in:
Bibliographic Details
Main Authors: Liegang Xia, Changge Chen, Jiancheng Luo, Xiaodong Hu, Xuanzhi Lu, Hongfeng Yu, Keyu Lu
Format: Article
Language:English
Published: Nature Portfolio 2025-06-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-03351-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849705178715914240
author Liegang Xia
Changge Chen
Jiancheng Luo
Xiaodong Hu
Xuanzhi Lu
Hongfeng Yu
Keyu Lu
author_facet Liegang Xia
Changge Chen
Jiancheng Luo
Xiaodong Hu
Xuanzhi Lu
Hongfeng Yu
Keyu Lu
author_sort Liegang Xia
collection DOAJ
description Abstract The precise extraction of crop type information on agricultural land supports applications such as agricultural information statistics and planning. It is also a crucial foundation for improving agricultural production efficiency and promoting agricultural informatization. In smallholder agricultural regions, such as the southern agricultural areas of China, a significant number of small parcels exist. These small parcels often exhibit deficiencies and discrepancies in feature representation for time series classification of crop types, leading to considerable classification challenges. To achieve more precise crop type differentiation in smallholder agricultural systems, this study designs a parcel-based classification framework, PITT (Parcel-level Integration of Time series and Texture). The PITT framework categorizes small parcels in smallholder systems by area into small parcels and micro parcels, which are then separately used as inputs for time series classification methods and high-resolution texture classification methods. During the process, the time series classification results guide the high-resolution texture classification method. Finally, the results from the texture classification are fused with the time series classification results, achieving more accurate crop classification outcomes. The study focuses on the Jiang area of Zongyang County, Tongling city, Anhui Province. Experimental validations using Pearson correlation coefficients and TWDTW similarity comparisons reveal that larger parcels have time series features that more strongly represent the features of typical samples. Additionally, when the PITT framework was compared with other time series classification models using real labels, the F1 scores for small parcels of approximately 0.1–0.5 hectares increased for rapeseed and wheat, reaching 0.93 and 0.94, respectively. For micro parcels (less than 0.1 ha), the F1 scores improved by at least 4.11% and 17.05%, respectively. This demonstrates the ability to achieve high crop classification performance with minimal labelling in smallholder systems, advancing the informatization of smallholder agriculture.
format Article
id doaj-art-8cd41c3c60c242c9a5526e89cfbb0442
institution DOAJ
issn 2045-2322
language English
publishDate 2025-06-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-8cd41c3c60c242c9a5526e89cfbb04422025-08-20T03:16:32ZengNature PortfolioScientific Reports2045-23222025-06-0115112410.1038/s41598-025-03351-7A precise spatiotemporal fusion crop classification framework based on parcelsLiegang Xia0Changge Chen1Jiancheng Luo2Xiaodong Hu3Xuanzhi Lu4Hongfeng Yu5Keyu Lu6College of Computer Science and Technology, Zhejiang University of TechnologyCollege of Computer Science and Technology, Zhejiang University of TechnologyState Key Laboratory of Remote Sensing Science, Aerospace Information Research Institute, Chinese Academy of SciencesSchool of Information and Electronic Engineering, Zhejiang University of Science and TechnologyState Key Laboratory of Remote Sensing Science, Aerospace Information Research Institute, Chinese Academy of SciencesSchool of Information and Electronic Engineering, Zhejiang University of Science and TechnologyCollege of Computer Science and Technology, Zhejiang University of TechnologyAbstract The precise extraction of crop type information on agricultural land supports applications such as agricultural information statistics and planning. It is also a crucial foundation for improving agricultural production efficiency and promoting agricultural informatization. In smallholder agricultural regions, such as the southern agricultural areas of China, a significant number of small parcels exist. These small parcels often exhibit deficiencies and discrepancies in feature representation for time series classification of crop types, leading to considerable classification challenges. To achieve more precise crop type differentiation in smallholder agricultural systems, this study designs a parcel-based classification framework, PITT (Parcel-level Integration of Time series and Texture). The PITT framework categorizes small parcels in smallholder systems by area into small parcels and micro parcels, which are then separately used as inputs for time series classification methods and high-resolution texture classification methods. During the process, the time series classification results guide the high-resolution texture classification method. Finally, the results from the texture classification are fused with the time series classification results, achieving more accurate crop classification outcomes. The study focuses on the Jiang area of Zongyang County, Tongling city, Anhui Province. Experimental validations using Pearson correlation coefficients and TWDTW similarity comparisons reveal that larger parcels have time series features that more strongly represent the features of typical samples. Additionally, when the PITT framework was compared with other time series classification models using real labels, the F1 scores for small parcels of approximately 0.1–0.5 hectares increased for rapeseed and wheat, reaching 0.93 and 0.94, respectively. For micro parcels (less than 0.1 ha), the F1 scores improved by at least 4.11% and 17.05%, respectively. This demonstrates the ability to achieve high crop classification performance with minimal labelling in smallholder systems, advancing the informatization of smallholder agriculture.https://doi.org/10.1038/s41598-025-03351-7Crop classificationAgricultural phenologyTime seriesSynthetic aperture radar (SAR)Object-based texture classification
spellingShingle Liegang Xia
Changge Chen
Jiancheng Luo
Xiaodong Hu
Xuanzhi Lu
Hongfeng Yu
Keyu Lu
A precise spatiotemporal fusion crop classification framework based on parcels
Scientific Reports
Crop classification
Agricultural phenology
Time series
Synthetic aperture radar (SAR)
Object-based texture classification
title A precise spatiotemporal fusion crop classification framework based on parcels
title_full A precise spatiotemporal fusion crop classification framework based on parcels
title_fullStr A precise spatiotemporal fusion crop classification framework based on parcels
title_full_unstemmed A precise spatiotemporal fusion crop classification framework based on parcels
title_short A precise spatiotemporal fusion crop classification framework based on parcels
title_sort precise spatiotemporal fusion crop classification framework based on parcels
topic Crop classification
Agricultural phenology
Time series
Synthetic aperture radar (SAR)
Object-based texture classification
url https://doi.org/10.1038/s41598-025-03351-7
work_keys_str_mv AT liegangxia aprecisespatiotemporalfusioncropclassificationframeworkbasedonparcels
AT changgechen aprecisespatiotemporalfusioncropclassificationframeworkbasedonparcels
AT jianchengluo aprecisespatiotemporalfusioncropclassificationframeworkbasedonparcels
AT xiaodonghu aprecisespatiotemporalfusioncropclassificationframeworkbasedonparcels
AT xuanzhilu aprecisespatiotemporalfusioncropclassificationframeworkbasedonparcels
AT hongfengyu aprecisespatiotemporalfusioncropclassificationframeworkbasedonparcels
AT keyulu aprecisespatiotemporalfusioncropclassificationframeworkbasedonparcels
AT liegangxia precisespatiotemporalfusioncropclassificationframeworkbasedonparcels
AT changgechen precisespatiotemporalfusioncropclassificationframeworkbasedonparcels
AT jianchengluo precisespatiotemporalfusioncropclassificationframeworkbasedonparcels
AT xiaodonghu precisespatiotemporalfusioncropclassificationframeworkbasedonparcels
AT xuanzhilu precisespatiotemporalfusioncropclassificationframeworkbasedonparcels
AT hongfengyu precisespatiotemporalfusioncropclassificationframeworkbasedonparcels
AT keyulu precisespatiotemporalfusioncropclassificationframeworkbasedonparcels