Rice is an important food crop for human beings.Accurately distinguishing different varieties and sowing methods of rice on a large scale can provide more accurate information for rice growth monitoring,yield estimati...Rice is an important food crop for human beings.Accurately distinguishing different varieties and sowing methods of rice on a large scale can provide more accurate information for rice growth monitoring,yield estimation,and phenological monitoring,which has significance for the development of modern agriculture.Compact polarimetric(CP)synthetic aperture radar(SAR)provides multichannel information and shows great potential for rice monitoring and mapping.Currently,the use of machine learning methods to build classification models is a controversial topic.In this paper,the advantages of CP SAR data,the powerful learning ability of machine learning,and the important factors of the rice growth cycle were taken into account to achieve high-precision and fine classification of rice paddies.First,CP SAR data were simulated by using the seven temporal RADARSAT-2 C-band data sets.Second,20-two CP SAR parameters were extracted from each of the seven temporal CP SAR data sets.In addition,we fully considered the change degree of CP SAR parameters on a time scale(ΔCP_(DoY)).Six machine learning methods were employed to carry out the fine classification of rice paddies.The results show that the classification methods of machine learning based on multitemporal CP SAR data can obtain better results in the fine classification of rice paddies by considering the parameters ofΔCP_(DoY).The overall accuracy is greater than 95.05%,and the Kappa coefficient is greater than 0.937.Among them,the random forest(RF)and support vector machine(SVM)achieve the best results,with an overall accuracy reaching 97.32%and 97.37%,respectively,and Kappa coefficient values reaching 0.965 and 0.966,respectively.For the two types of rice paddies,the average accuracy of the transplant hybrid(T-H)rice paddy is greater than 90.64%,and the highest accuracy is 95.95%.The average accuracy of direct-sown japonica(D-J)rice paddy is greater than 92.57%,and the highest accuracy is 96.13%.展开更多
Understanding species distribution in large forest ecosystems is fundamental for biodiversity conservation,biomass estimation,climate regulation,soil and water conservation.While remote sensing combined with modeling ...Understanding species distribution in large forest ecosystems is fundamental for biodiversity conservation,biomass estimation,climate regulation,soil and water conservation.While remote sensing combined with modeling algorithms enables efi cient forest monitoring,existing approaches frequently treat multi-temporal imagery as one-dimensional sequences,capturing only temporal trends within spectral bands and neglecting the joint spectraltemporal dynamics essential for fine-scale forest classification.Moreover,single-model frameworks frequently suffer from limited generalization and low reliability when applied to complex,largescale regions.To address these challenges,this study proposes an ensemble classification framework integrating two-dimensional feature reconstruction and multi-classifier fusion.Spectral and temporal dimensions were jointly encoded to enhance feature representation,and an ensemble learning strategy was introduced to improve model robustness and adaptability.The framework comprises a feature extraction module and an ensemble classification module.Using Sentinel-1 and Sentinel-2 satellite imagery acquired between 2021 and 2022 and field survey data,two datasets were constructed to evaluate model performance.The proposed method achieved overall accuracies of 97.84%and 91.41%on the two datasets,respectively.Outputting and integrating the results of multiple classifiers provides insights into the model's classification mechanism,results proved the effectiveness of the feature extraction module and the differences among the integration strategies.The Simpson index was employed for visual evaluation,overcoming sample labelling limitations,and the influence of elevation and slope on vegetation was analysed,highlighting the necessity for topographic features in mountainous areas.展开更多
基金funded in part by the National Natural Science Foundation of China(Grant No.41871272).
文摘Rice is an important food crop for human beings.Accurately distinguishing different varieties and sowing methods of rice on a large scale can provide more accurate information for rice growth monitoring,yield estimation,and phenological monitoring,which has significance for the development of modern agriculture.Compact polarimetric(CP)synthetic aperture radar(SAR)provides multichannel information and shows great potential for rice monitoring and mapping.Currently,the use of machine learning methods to build classification models is a controversial topic.In this paper,the advantages of CP SAR data,the powerful learning ability of machine learning,and the important factors of the rice growth cycle were taken into account to achieve high-precision and fine classification of rice paddies.First,CP SAR data were simulated by using the seven temporal RADARSAT-2 C-band data sets.Second,20-two CP SAR parameters were extracted from each of the seven temporal CP SAR data sets.In addition,we fully considered the change degree of CP SAR parameters on a time scale(ΔCP_(DoY)).Six machine learning methods were employed to carry out the fine classification of rice paddies.The results show that the classification methods of machine learning based on multitemporal CP SAR data can obtain better results in the fine classification of rice paddies by considering the parameters ofΔCP_(DoY).The overall accuracy is greater than 95.05%,and the Kappa coefficient is greater than 0.937.Among them,the random forest(RF)and support vector machine(SVM)achieve the best results,with an overall accuracy reaching 97.32%and 97.37%,respectively,and Kappa coefficient values reaching 0.965 and 0.966,respectively.For the two types of rice paddies,the average accuracy of the transplant hybrid(T-H)rice paddy is greater than 90.64%,and the highest accuracy is 95.95%.The average accuracy of direct-sown japonica(D-J)rice paddy is greater than 92.57%,and the highest accuracy is 96.13%.
基金supported by National Natural Science Foundation of China[Grants Nos.42130113 and 42371398]the Basic Research Innovative Groups of Gansu Province,China[Grant No.21JR7RA068].
文摘Understanding species distribution in large forest ecosystems is fundamental for biodiversity conservation,biomass estimation,climate regulation,soil and water conservation.While remote sensing combined with modeling algorithms enables efi cient forest monitoring,existing approaches frequently treat multi-temporal imagery as one-dimensional sequences,capturing only temporal trends within spectral bands and neglecting the joint spectraltemporal dynamics essential for fine-scale forest classification.Moreover,single-model frameworks frequently suffer from limited generalization and low reliability when applied to complex,largescale regions.To address these challenges,this study proposes an ensemble classification framework integrating two-dimensional feature reconstruction and multi-classifier fusion.Spectral and temporal dimensions were jointly encoded to enhance feature representation,and an ensemble learning strategy was introduced to improve model robustness and adaptability.The framework comprises a feature extraction module and an ensemble classification module.Using Sentinel-1 and Sentinel-2 satellite imagery acquired between 2021 and 2022 and field survey data,two datasets were constructed to evaluate model performance.The proposed method achieved overall accuracies of 97.84%and 91.41%on the two datasets,respectively.Outputting and integrating the results of multiple classifiers provides insights into the model's classification mechanism,results proved the effectiveness of the feature extraction module and the differences among the integration strategies.The Simpson index was employed for visual evaluation,overcoming sample labelling limitations,and the influence of elevation and slope on vegetation was analysed,highlighting the necessity for topographic features in mountainous areas.
