{"title":"基于光谱估算叶绿素含量并确定低覆盖率水稻的背景干扰机制","authors":"","doi":"10.1016/j.compag.2024.109442","DOIUrl":null,"url":null,"abstract":"<div><p>The chlorophyll content is a vital indicator of rice growth and nutritional status. However, estimating the rice chlorophyll content using spectral-based techniques at the early tillering stage is challenging because of background interference. Using the energy conservation principle, this study explained the spectral variation and background interference mechanisms of clear, muddy, and green algae-covered backgrounds. We developed mathematical interference models for the three types of backgrounds and determined their interference degree and influence mode. We developed rice chlorophyll content estimation models for unclassified and classified (clear, muddy, and green algae-covered) backgrounds using 12 preprocessing, four wavelength selection, and three modeling methods, and we explored the importance of background classification. Moreover, we found that the optimal chlorophyll content estimation model for the clear background was SS+UVE+CNN, with R<sup>2</sup> and RMSE values of 0.786 and 13.191 in the training set and 0.741 and 15.327 in the test set, respectively; that for the muddy background was MSC+GA+CNN, with R<sup>2</sup> and RMSE values of 0.914 and 10.425 in the training set and 0.660 and 16.844 in the test set, respectively; and that for the green algae-covered background was DC+GA+CNN, with R<sup>2</sup> and RMSE values of 0.904 and 9.111 in the training set and 0.688 and 17.694 in the test set, respectively. Our study could provide valuable insights into reducing and correcting background interference during proximal remote sensing data collection.</p></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":null,"pages":null},"PeriodicalIF":7.7000,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Spectral-based estimation of chlorophyll content and determination of background interference mechanisms in low-coverage rice\",\"authors\":\"\",\"doi\":\"10.1016/j.compag.2024.109442\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>The chlorophyll content is a vital indicator of rice growth and nutritional status. However, estimating the rice chlorophyll content using spectral-based techniques at the early tillering stage is challenging because of background interference. Using the energy conservation principle, this study explained the spectral variation and background interference mechanisms of clear, muddy, and green algae-covered backgrounds. We developed mathematical interference models for the three types of backgrounds and determined their interference degree and influence mode. We developed rice chlorophyll content estimation models for unclassified and classified (clear, muddy, and green algae-covered) backgrounds using 12 preprocessing, four wavelength selection, and three modeling methods, and we explored the importance of background classification. Moreover, we found that the optimal chlorophyll content estimation model for the clear background was SS+UVE+CNN, with R<sup>2</sup> and RMSE values of 0.786 and 13.191 in the training set and 0.741 and 15.327 in the test set, respectively; that for the muddy background was MSC+GA+CNN, with R<sup>2</sup> and RMSE values of 0.914 and 10.425 in the training set and 0.660 and 16.844 in the test set, respectively; and that for the green algae-covered background was DC+GA+CNN, with R<sup>2</sup> and RMSE values of 0.904 and 9.111 in the training set and 0.688 and 17.694 in the test set, respectively. Our study could provide valuable insights into reducing and correcting background interference during proximal remote sensing data collection.</p></div>\",\"PeriodicalId\":50627,\"journal\":{\"name\":\"Computers and Electronics in Agriculture\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":7.7000,\"publicationDate\":\"2024-09-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computers and Electronics in Agriculture\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0168169924008330\",\"RegionNum\":1,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"AGRICULTURE, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computers and Electronics in Agriculture","FirstCategoryId":"97","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0168169924008330","RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRICULTURE, MULTIDISCIPLINARY","Score":null,"Total":0}
Spectral-based estimation of chlorophyll content and determination of background interference mechanisms in low-coverage rice
The chlorophyll content is a vital indicator of rice growth and nutritional status. However, estimating the rice chlorophyll content using spectral-based techniques at the early tillering stage is challenging because of background interference. Using the energy conservation principle, this study explained the spectral variation and background interference mechanisms of clear, muddy, and green algae-covered backgrounds. We developed mathematical interference models for the three types of backgrounds and determined their interference degree and influence mode. We developed rice chlorophyll content estimation models for unclassified and classified (clear, muddy, and green algae-covered) backgrounds using 12 preprocessing, four wavelength selection, and three modeling methods, and we explored the importance of background classification. Moreover, we found that the optimal chlorophyll content estimation model for the clear background was SS+UVE+CNN, with R2 and RMSE values of 0.786 and 13.191 in the training set and 0.741 and 15.327 in the test set, respectively; that for the muddy background was MSC+GA+CNN, with R2 and RMSE values of 0.914 and 10.425 in the training set and 0.660 and 16.844 in the test set, respectively; and that for the green algae-covered background was DC+GA+CNN, with R2 and RMSE values of 0.904 and 9.111 in the training set and 0.688 and 17.694 in the test set, respectively. Our study could provide valuable insights into reducing and correcting background interference during proximal remote sensing data collection.
期刊介绍:
Computers and Electronics in Agriculture provides international coverage of advancements in computer hardware, software, electronic instrumentation, and control systems applied to agricultural challenges. Encompassing agronomy, horticulture, forestry, aquaculture, and animal farming, the journal publishes original papers, reviews, and applications notes. It explores the use of computers and electronics in plant or animal agricultural production, covering topics like agricultural soils, water, pests, controlled environments, and waste. The scope extends to on-farm post-harvest operations and relevant technologies, including artificial intelligence, sensors, machine vision, robotics, networking, and simulation modeling. Its companion journal, Smart Agricultural Technology, continues the focus on smart applications in production agriculture.