Artificial neural network for estimating leaf fresh weight of rice plant through visual-nir imaging

TANUJ MISRA; ALKA ARORA; SUDEEP MARWAHA; MRINMOY RAY; DHANDAPANI RAJU; SUDHIR KUMAR; SWATI GOEL; RABI NARAYAN SAHOO; VISWANATHAN CHINNUSAMY

doi:10.56093/ijas.v89i10.94631

Authors

TANUJ MISRA PhD Scholar, ICAR-Indian Agricultural Statistics Research Institute, New Delhi 110 012, India
ALKA ARORA Principal Scientist, ICAR-Indian Agricultural Statistics Research Institute, New Delhi 110 012, India
SUDEEP MARWAHA Principal Scientist, ICAR-Indian Agricultural Statistics Research Institute, New Delhi 110 012, India
MRINMOY RAY Scientist, ICAR-Indian Agricultural Statistics Research Institute, New Delhi 110 012, India
DHANDAPANI RAJU Scientist, ICAR-Indian Agricultural Statistics Research Institute, New Delhi 110 012, India
SUDHIR KUMAR Scientist, ICAR-Indian Agricultural Statistics Research Institute, New Delhi 110 012, India
SWATI GOEL Research Scholar, ICAR-IARI, New Delhi
RABI NARAYAN SAHOO Principal Scientist, ICAR-Indian Agricultural Statistics Research Institute, New Delhi 110 012, India
VISWANATHAN CHINNUSAMY Principal Scientist, Head, ICAR-Indian Agricultural Statistics Research Institute, New Delhi 110 012, India

https://doi.org/10.56093/ijas.v89i10.94631

Keywords:

Artificial neural network, Green leaf proportion, Image analysis, LFW, Non-destructive phenotyping, Rice

Abstract

Prediction of fresh biomass is the key for evaluation of the response of crop genotypes to diverse input and stress conditions, and forms basis for calculating net primary production. Hence, accurate and high throughput estimation of fresh biomass is critical for plant phenotyping. As conventional phenotyping approaches for measuring fresh biomass is time consuming, laborious and destructive, image based phenotyping methods are being widely used now in plant phenotyping. However, current approaches for estimating fresh biomass of plants are based on projected shoot area estimated from the visual (VIS) image. These approaches do not consider the water content of the plant tissues which are about 70-80% in leafy vegetation. Since water absorbs radiation in the Near Infra-Red (NIR) (900â€“1700 nm) region, it has been hypothesized that combined use of VIS and NIR imaging can predict the fresh biomass more accurately that the VIS image alone. In this study, VIS and NIR imaging were captured for rice leaves with different moisture content as a test case. For background subtraction from NIR image, PlantCV v2 NIR imaging algorithm was implemented in MATLAB software (version 2015b). The proposed image derived parameter, viz. Green Leaf Proportion (GLP) from VIS image and mean gray value/intensity (NIR_MGI) from NIR image were used as input to develop Artificial Neural Network (ANN) model to estimate the Leaf Fresh Weight (LFW). This proposed approach significantly enhanced the fresh biomass prediction as compared to the conventional regression technique based on projected shoot area derived from VIS image.

Downloads

Download data is not yet available.

References

Bruinsma J. 2003. World Agriculture Towards 2015/2030 an FAO perspective. Earthscan, London.

Behera S K, Meher S K and Park H S. 2015. Artificial neural network model for predicting methane percentage in biogas recovered from a landfill upon injection of liquid organic waste. Clean Technologies and Environmental Policy 17(2): 443–53. DOI: https://doi.org/10.1007/s10098-014-0798-4

Ebrahimi M, Sinegani A A S, Sarikhani M R and Mohammadi S A. 2017. Comparison of artificial neural network and multivariate regression models for prediction of Azotobacteria population in soil under different land uses. Computers and Electronics in Agriculture 140: 409–21. DOI: https://doi.org/10.1016/j.compag.2017.06.019

Fernández R, Montes H and Salinas C. 2015. VIS-NIR, SWIR and LWIR imagery for estimation of ground bearing capacity. Sensors 15(6): 13994–14015. DOI: https://doi.org/10.3390/s150613994

Furbank R T, von Caemmerer S, Sheehy J and Edwards G. 2009. C4 rice: a challenge for plant phenomics. Functional Plant Biology 36(11): 845–56. DOI: https://doi.org/10.1071/FP09185

Gehan M A, Fahlgren N, Abbasi A, Berry J C, Callen S T, Chavez L and Hoyer J S. 2017. PlantCV v2: Image analysis software for high-throughput plant phenotyping. PeerJ 5: e4088. DOI: https://doi.org/10.7717/peerj.4088

Golzarian M R, Frick R A, Rajendran K, Berger B, Roy S, Tester M and Lun D S. 2011. Accurate inference of shoot biomass from high-throughput images of cereal plants. Plant Methods 7: 1–11. DOI: https://doi.org/10.1186/1746-4811-7-2

Jansen M, Gilmer F, Biskup B, Nagel K A, Rascher U, Fischbach A and De Jaeger I. 2009. Simultaneous phenotyping of leaf growth and chlorophyll fluorescence via GROWSCREEN FLUORO allows detection of stress tolerance in Arabidopsis thaliana and other rosette plants. Functional Plant Biology 36(11): 902–14. DOI: https://doi.org/10.1071/FP09095

Lillesand T, Kiefer R W and Chipman J. 2015. Remote sensing and image interpretation. John Wiley & Sons.

Mizoue N and Masutani T. 2003. Image analysis measure of crown condition, foliage biomass and stem growth relationships of Chamaecyparis obtusa. Forest Ecology and Management 172(1): 79–88 DOI: https://doi.org/10.1016/S0378-1127(02)00281-5

Niklas K J and Enquist B J. 2002. On the vegetative biomass partitioning of seed plant leaves, stems, and roots. The American Naturalist 159(5): 482–97. DOI: https://doi.org/10.1086/339459

Otsu N. (1979). A threshold selection method from gray-level histograms. IEEE transactions on systems, man, and cybernetics 9(1): 62-66. DOI: https://doi.org/10.1109/TSMC.1979.4310076

Paruelo J M, Lauenroth W K and Roset P A. 2000. Estimating aboveground plant biomass using a photographic technique. Journal of Range Management Archives 53(2): 190–3. DOI: https://doi.org/10.2307/4003281

Poorter H and Nagel O. 2000. The role of biomass allocation in the growth response of plants to different levels of light, CO2, nutrients and water: a quantitative review. Functional Plant Biology 27(12): 1191. DOI: https://doi.org/10.1071/PP99173_CO

Ray M, Rai A, Ramasubramanian V and Singh K N. 2016. ARIMA-WNN hybrid model for forecasting wheat yield time series data. Journal of the Indian Society of Agricultural Statistic 70(1): 63–70.

Schirrmann M, Hamdorf A, Garz A, Ustyuzhanin A and Dammer K H. 2016. Estimating wheat biomass by combining image clustering with crop height. Computers and Electronics in Agriculture 121: 374–84. DOI: https://doi.org/10.1016/j.compag.2016.01.007

Seelig H D, Hoehn A, Stodieck L S, Klaus D M, Adams Iii W W, and Emery W J. 2008. The assessment of leaf water content using leaf reflectance ratios in the visible, near, and shortwaveinfrared. International Journal of Remote Sensing 29(13): 3701–13. DOI: https://doi.org/10.1080/01431160701772500

Stenberg B, Rossel R A V, Mouazen A M and Wetterlind J. 2010. Visible and near infrared spectroscopy in soil science. In Advances in agronomy 107: 163–215. DOI: https://doi.org/10.1016/S0065-2113(10)07005-7

Sticklen M B. 2007. Feedstock crop genetic engineering for alcohol fuels. Crop science 47(6): 2238–48. DOI: https://doi.org/10.2135/cropsci2007.04.0212

Teodoro A C. 2015. Applicability of data mining algorithms in the identification of beach features/patterns on high-resolution satellite data. Journal of Applied Remote Sensing 9(1): 095095. DOI: https://doi.org/10.1117/1.JRS.9.095095

Tsaftaris S A, Minervini M and Scharr H. 2016. Machine learning for plant phenotyping needs image processing. Trends in plant science 21(12): 989–91. DOI: https://doi.org/10.1016/j.tplants.2016.10.002