Lei Tong, Jun Zhou, S. Bai, Chengyuan Xu, Y. Qian, Yongsheng Gao, Zhihong Xu
{"title":"Automatic Estimation of Soil Biochar Quantity via Hyperspectral Imaging","authors":"Lei Tong, Jun Zhou, S. Bai, Chengyuan Xu, Y. Qian, Yongsheng Gao, Zhihong Xu","doi":"10.4018/978-1-4666-9435-4.CH011","DOIUrl":null,"url":null,"abstract":"Biochar soil amendment is globally recognized as an emerging approach to mitigate CO2 emissions and increase crop yield. Because the durability and changes of biochar may affect its long term functions, it is important to quantify biochar in soil after application. In this chapter, an automatic soil biochar estimation method is proposed by analysis of hyperspectral images captured by cameras that cover both visible and infrared light wavelengths. The soil image is considered as a mixture of soil and biochar signals, and then hyperspectral unmixing methods are applied to estimate the biochar proportion at each pixel. The final percentage of biochar can be calculated by taking the mean of the proportion of hyperspectral pixels. Three different models of unmixing are described in this chapter. Their experimental results are evaluated by polynomial regression and root mean square errors against the ground truth data collected in the environmental labs. The results show that hyperspectral unmixing is a promising method to measure the percentage of biochar in the soil.","PeriodicalId":54004,"journal":{"name":"International Journal of Agricultural and Environmental Information Systems","volume":"30 1","pages":""},"PeriodicalIF":1.3000,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Agricultural and Environmental Information Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4018/978-1-4666-9435-4.CH011","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 1
Abstract
Biochar soil amendment is globally recognized as an emerging approach to mitigate CO2 emissions and increase crop yield. Because the durability and changes of biochar may affect its long term functions, it is important to quantify biochar in soil after application. In this chapter, an automatic soil biochar estimation method is proposed by analysis of hyperspectral images captured by cameras that cover both visible and infrared light wavelengths. The soil image is considered as a mixture of soil and biochar signals, and then hyperspectral unmixing methods are applied to estimate the biochar proportion at each pixel. The final percentage of biochar can be calculated by taking the mean of the proportion of hyperspectral pixels. Three different models of unmixing are described in this chapter. Their experimental results are evaluated by polynomial regression and root mean square errors against the ground truth data collected in the environmental labs. The results show that hyperspectral unmixing is a promising method to measure the percentage of biochar in the soil.