Multi-Temporal Monsoon Crop Biomass Estimation Using Hyperspectral Imaging
Hyperspectral remote sensing is considered to be an effective tool in crop monitoring and estimation of biomass. Many of the previous approaches are from single year or single date measurements, even though the complete crop growth with multiple years would be required for an appropriate estimation...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/11/15/1771 |
| _version_ | 1819002597278744576 |
|---|---|
| author | Supriya Dayananda Thomas Astor Jayan Wijesingha Subbarayappa Chickadibburahalli Thimappa Hanumanthappa Dimba Chowdappa Mudalagiriyappa Rama Rao Nidamanuri Sunil Nautiyal Michael Wachendorf |
| author_facet | Supriya Dayananda Thomas Astor Jayan Wijesingha Subbarayappa Chickadibburahalli Thimappa Hanumanthappa Dimba Chowdappa Mudalagiriyappa Rama Rao Nidamanuri Sunil Nautiyal Michael Wachendorf |
| author_sort | Supriya Dayananda |
| collection | DOAJ |
| description | Hyperspectral remote sensing is considered to be an effective tool in crop monitoring and estimation of biomass. Many of the previous approaches are from single year or single date measurements, even though the complete crop growth with multiple years would be required for an appropriate estimation of biomass. The aim of this study was to estimate the fresh matter biomass (FMB) by terrestrial hyperspectral imaging of the three crops (lablab, maize and finger millet) under different levels of nitrogen fertiliser and water supply. Further, the importance of the different spectral regions for the estimation of FMB was assessed. The study was conducted in two experimental layouts (rainfed (R) and irrigated (I)) at the University of Agricultural Sciences, Bengaluru, India. Spectral images and the FMB were collected over three years (2016−2018) during the growing season of the crops. Random forest regression method was applied to build FMB models. R² validation (R²<sub>val</sub>) and relative root mean square error prediction (rRMSEP) was used to evaluate the FMB models. The Generalised model (combination of R and I data) performed better for lablab (R²<sub>val</sub> = 0.53, rRMSEP = 13.9%), maize (R²<sub>val</sub> = 0.53, rRMSEP = 18.7%) and finger millet (R²<sub>val</sub> = 0.46, rRMSEP = 18%) than the separate FMB models for R and I. In the best derived model, the most important variables contributing to the estimation of biomass were in the wavelength ranges of 546−910 nm (lablab), 750−794 nm (maize) and 686−814 nm (finger millet). The deviation of predicted and measured FMB did not differ much among the different levels of N and water supply. However, there was a trend of overestimation at the initial stage and underestimation at the later stages of crop growth. |
| first_indexed | 2024-12-20T23:07:38Z |
| format | Article |
| id | doaj.art-5982621c67c842a8a7f4f00e262ee5d6 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-20T23:07:38Z |
| publishDate | 2019-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-5982621c67c842a8a7f4f00e262ee5d62022-12-21T19:23:49ZengMDPI AGRemote Sensing2072-42922019-07-011115177110.3390/rs11151771rs11151771Multi-Temporal Monsoon Crop Biomass Estimation Using Hyperspectral ImagingSupriya Dayananda0Thomas Astor1Jayan Wijesingha2Subbarayappa Chickadibburahalli Thimappa3Hanumanthappa Dimba Chowdappa4Mudalagiriyappa5Rama Rao Nidamanuri6Sunil Nautiyal7Michael Wachendorf8Grassland Science and Renewable Plant Resources, Organic Agricultural Sciences, Universität Kassel, D-37213 Witzenhausen, GermanyGrassland Science and Renewable Plant Resources, Organic Agricultural Sciences, Universität Kassel, D-37213 Witzenhausen, GermanyGrassland Science and Renewable Plant Resources, Organic Agricultural Sciences, Universität Kassel, D-37213 Witzenhausen, GermanyDepartment of Soil Science and Agricultural Chemistry, University of Agricultural Sciences (UAS), GKVK, Bengaluru 560065, Karnataka, IndiaAll-India Coordinated Research Project on Agroforestry, University of Agricultural Sciences (UAS), GKVK, Bengaluru 560065, Karnataka, IndiaAll-India Coordinated Research Project on Dryland Agriculture, University of Agricultural Sciences (UAS), GKVK, Bengaluru 560065, Karnataka, IndiaDepartment of Earth and Space Sciences, Indian Institute of Space Science and Technology, Valiyamala, Thiruvananthapuram 695574, Kerala, IndiaCentre for Ecological Economics and Natural Resources, Institute for Social and Economic Change, Dr. VKRV Rao Road, Nagarabhavi, Bengaluru 560072, Karnataka, IndiaGrassland Science and Renewable Plant Resources, Organic Agricultural Sciences, Universität Kassel, D-37213 Witzenhausen, GermanyHyperspectral remote sensing is considered to be an effective tool in crop monitoring and estimation of biomass. Many of the previous approaches are from single year or single date measurements, even though the complete crop growth with multiple years would be required for an appropriate estimation of biomass. The aim of this study was to estimate the fresh matter biomass (FMB) by terrestrial hyperspectral imaging of the three crops (lablab, maize and finger millet) under different levels of nitrogen fertiliser and water supply. Further, the importance of the different spectral regions for the estimation of FMB was assessed. The study was conducted in two experimental layouts (rainfed (R) and irrigated (I)) at the University of Agricultural Sciences, Bengaluru, India. Spectral images and the FMB were collected over three years (2016−2018) during the growing season of the crops. Random forest regression method was applied to build FMB models. R² validation (R²<sub>val</sub>) and relative root mean square error prediction (rRMSEP) was used to evaluate the FMB models. The Generalised model (combination of R and I data) performed better for lablab (R²<sub>val</sub> = 0.53, rRMSEP = 13.9%), maize (R²<sub>val</sub> = 0.53, rRMSEP = 18.7%) and finger millet (R²<sub>val</sub> = 0.46, rRMSEP = 18%) than the separate FMB models for R and I. In the best derived model, the most important variables contributing to the estimation of biomass were in the wavelength ranges of 546−910 nm (lablab), 750−794 nm (maize) and 686−814 nm (finger millet). The deviation of predicted and measured FMB did not differ much among the different levels of N and water supply. However, there was a trend of overestimation at the initial stage and underestimation at the later stages of crop growth.https://www.mdpi.com/2072-4292/11/15/1771Cash cropsHyperspectral imagingBiomass predictionMachine learning |
| spellingShingle | Supriya Dayananda Thomas Astor Jayan Wijesingha Subbarayappa Chickadibburahalli Thimappa Hanumanthappa Dimba Chowdappa Mudalagiriyappa Rama Rao Nidamanuri Sunil Nautiyal Michael Wachendorf Multi-Temporal Monsoon Crop Biomass Estimation Using Hyperspectral Imaging Remote Sensing Cash crops Hyperspectral imaging Biomass prediction Machine learning |
| title | Multi-Temporal Monsoon Crop Biomass Estimation Using Hyperspectral Imaging |
| title_full | Multi-Temporal Monsoon Crop Biomass Estimation Using Hyperspectral Imaging |
| title_fullStr | Multi-Temporal Monsoon Crop Biomass Estimation Using Hyperspectral Imaging |
| title_full_unstemmed | Multi-Temporal Monsoon Crop Biomass Estimation Using Hyperspectral Imaging |
| title_short | Multi-Temporal Monsoon Crop Biomass Estimation Using Hyperspectral Imaging |
| title_sort | multi temporal monsoon crop biomass estimation using hyperspectral imaging |
| topic | Cash crops Hyperspectral imaging Biomass prediction Machine learning |
| url | https://www.mdpi.com/2072-4292/11/15/1771 |
| work_keys_str_mv | AT supriyadayananda multitemporalmonsooncropbiomassestimationusinghyperspectralimaging AT thomasastor multitemporalmonsooncropbiomassestimationusinghyperspectralimaging AT jayanwijesingha multitemporalmonsooncropbiomassestimationusinghyperspectralimaging AT subbarayappachickadibburahallithimappa multitemporalmonsooncropbiomassestimationusinghyperspectralimaging AT hanumanthappadimbachowdappa multitemporalmonsooncropbiomassestimationusinghyperspectralimaging AT mudalagiriyappa multitemporalmonsooncropbiomassestimationusinghyperspectralimaging AT ramaraonidamanuri multitemporalmonsooncropbiomassestimationusinghyperspectralimaging AT sunilnautiyal multitemporalmonsooncropbiomassestimationusinghyperspectralimaging AT michaelwachendorf multitemporalmonsooncropbiomassestimationusinghyperspectralimaging |