Random Forest Spatial Interpolation Techniques for Crop Yield  Estimation at District Level

Naveen G. P.; Prachi Misra Sahoo; Pankaj Das; Tauqueer Ahmad; Ankur Biswas

doi:10.56093/jisas.v78i01.171308

Authors

Naveen G. P. ICAR-Indian Agricultural Statistics Research Institute, New Delhi
Prachi Misra Sahoo ICAR-Indian Agricultural Statistics Research Institute, New Delhi
Pankaj Das ICAR-Indian Agricultural Statistics Research Institute, New Delhi
Tauqueer Ahmad ICAR-Indian Agricultural Statistics Research Institute, New Delhi
Ankur Biswas ICAR-Indian Agricultural Statistics Research Institute, New Delhi

https://doi.org/10.56093/jisas.v78i01.171308

Abstract

General Crop Estimation Surveys (GCES) based on Crop Cutting Experiments (CCEs) are conducted for estimation of crop yield following random sampling approach for almost all major crops. About 13 lakh CCEs are conducted every year which has now increased rapidly due to the Pradhan Mantri Fasal Bima Yojana (PMFBY) which is yield based insurance scheme. As suggested by Ministry of Agriculture and Farmers’ Welfare (MoA&FW), this number needs to be reduced drastically by developing sampling procedures based on the use of advanced technologies and advanced survey techniques for crop yield estimation. In this study, an attempt has been made to develop crop yield estimation procedures using Random Forest Spatial Interpolation (RFSI) technique including the spatial variables like spatial distance and nearest neighbours as covariates. RFSI is one of the most adaptable and user-friendly interpolation techniques, as well as one of the fastest in large training datasets. Estimates of yield of wheat were obtained for all the six tehsils of Barabanki district using the estimator under stratified two stage sampling technique. The district level estimates were also obtained by pooling area under wheat crop in each tehsil along with the district level estimate of crop yield, estimate of variance, estimate of standard error (SE) and percentage SE (%SE) of these estimates were also computed in order to make comparison. The results of this study suggest that the estimates derived using RFSI are comparable to kriging and superior to inverse distance weighting (IDW) for the prediction of yield at unknown locations using distance and nearest neighbours.

Downloads

Download data is not yet available.

References

Aditya, K., Chandra, H. and Basak, P., Kumari, V. and Das, S. (2020). District level crop yield estimation with reduced number of crop

cutting experiments. Indian J. Agric. Sci., 90(6), 1185-1189.

Aditya K., Biswas A., Gupta A.K. and Chandra, H. (2017). District level crop yield estimation using calibration approach. Curr. Sci., 112(9), 1927.

Ahmad T. and Kathuria O.P. (2010). Estimation of crop yield at block level. J Appl Res., 2(2), 164-172.

Ahmad T., Sahoo P.M., Rai A., Chandra H. and Biswas A. (2020). Integrated Sampling Methodology for Crop Yield Estimation using Remote Sensing, Field Surveys and Weather Parameters for Crop Insurance. Final Report, ICAR-IASRI publication, New Delhi.

Bahmani S., Naganna S.R., Ghorbani M.A., Shahabi M., Asadi E. and Shahid S. (2021). Geographically Weighted Regression Hybridized with Kriging Model for Delineation of Drought-Prone Areas. Environ. Model. Assess., 26(5), 803-821.

Bazzi C.L., Martins M.R., Cordeiro B.E., Gebler L., De Souza E.G., Schenatto K. and Sobjak R. (2021). Yield map generation of perennial crops for fresh consumption. Precis. Agric., 92, 1-14.

Biswas A. (2014). A study of spatial bootstrap techniques for variance estimation in finite population. Unpublished Ph.D. thesis, P.G. School, ICAR-IARI, New Delhi, 74(3), 227-236.

Biswas A., Rai A., Ahmad T. and Sahoo P.M. (2017). Spatial estimation and rescaled spatial bootstrap approach for finite population. Commun Stat-Theor M., 46(1), 373-388.k

Naveen G. P et al. / Journal of the Indian Society of Agricultural Statistics 78(1) 2024 9–19Čeh M., Kilibarda M., Lisec A. and Bajat B. (2018). Estimating the performance of random forest versus multiple regression for predicting prices of the apartments. ISPRS Int. J. Geoinf., 7(5),168.19

Kingra P.K., Setia R., Kaur J., Pal R.K. and Singh S.P. (2021). Role of geospatial technology in crop growth monitoring and yield

estimation. In Re-envisioning Remote Sensing Applications, 42, 273-290.

Chen F.W. and Liu C.W. (2012). Estimation of the spatial rainfall distribution using inverse distance weighting (IDW) in the middle of Taiwan. Paddy Water Environ., 10(3), 209-222.

Cho J.B., Guinness J., Kharel T.P., Sunoj S., Kharel D., Oware E.K. and Ketterings Q.M. (2021). Spatial estimation methods for mapping corn silage and grain yield monitor data. Precis. Agric., 22, 1501-1520.

Dela Torre D.M.G., Gao J. and Macinnis-Ng C. (2021). Remote sensing-based estimation of rice yields using various models. A

critical review. Geo-Spat., 18, 1-24.

Donald, S. (1968). A two-dimensional interpolation functions for irregularly-spaced data. Proceedings of the 1968 Association for Computing Machinery (ACM)., 68, 517-524.

Elhag A. and Abdelhadi A. (2018). Monitoring and Yield Estimation of Sugarcane using Remote Sensing and GIS. Am. J. Eng. Res., 7(1), 170-179.

Georganos S., Grippa T., NiangGadiaga A., Linard C., Lennert M., Vanhuysse S. and Kalogirou S. (2021). Geographical random forests: a spatial extension of the random forest algorithm to address spatial heterogeneity in remote sensing and population

modelling. Geocarto Int., 36(2), 121-136.

Gia Pham T., Kappas M., Van Huynh C. and Hoang Khan Nguyen L. (2019). Application of ordinary kriging and regression kriging method for soil properties mapping in hilly region of Central Vietnam. ISPRSInt. J. Geoinf., 8(3), 147.

Goovaerts P. (2000). Geostatistical approaches for incorporating elevation into the spatial interpolation of rainfall. J. Hydrol., 228(1-2), 113-129.

Gupta N.K. (2007). On spatial prediction modeling. Unpublished Ph.D. Thesis of P.G. School, ICAR-IARI, New Delhi. Hamer W.B., Birr T., Verreet J.A., Duttmann R. and Klink H. (2020). Spatio-temporal prediction of the epidemic spread of dangerous pathogens using machine learning methods. ISPRS Int. J. Geoinf., 9(1), 44.

Hassan S.S. and Goheer M.A. (2021). Modeling and monitoring wheat crop yield using geospatial techniques: a case study of Potohar

region, Pakistan. J. Indian Soc. Remote., 49(1), 1-12.

He X., Chaney N.W., Schleiss M. and Sheffield J. (2016). Spatial downscaling of precipitation using adaptable random forests. Water Resour. Res., 52(10), 8217-8237.

Hengl T., Nussbaum, M. Wright M.N., Heuvelink G.B. and Gräler B. (2018). Random forest as a generic framework for predictive modeling of spatial and spatio-temporal variables. PeerJ., 6, e5518.

Huang G. (2021). Missing data filling method based on linear interpolation and lightgbm. Water Resour. Res., 1754(2021) 012187, 1-6.

Jeong J.H., Resop J.P., Mueller N.D., Fleisher D.H., Yun K., Butler E.E. and Kim S.H. (2016). Random forests for global and regional crop

yield predictions. PLoS One., 11(6), 1-15.

Laslett G.M. (1994). Kriging and splines: an empirical comparison of their predictive performance in some applications. Am. Stat. Assoc. Bull., 89(426), 391-400.

Li J., Heap A.D., Potter A. and Daniell J.J. (2011). Application of machine learning methods to spatial interpolation of environmental variables. Environ Model Softw., 26(12), 1647-1659.

Li J., Alvarez B., Siwabessy J., Tran M., Huang Z., Przeslawski R. and Nichol S. (2017). Application of random forest generalised linear

model and their hybrid methods with geo-statistical techniques to count data: Predicting sponge species richness. Environ Model

Softw., 97, 112-129.

Mahmoudzadeh H., Matinfar H.R., Taghizadeh-Mehrjardi R., and Kerry R. (2020). Spatial prediction of soil organic carbon using

machine learning techniques in Western Iran. Geoderma Reg., 21, 106736.

Mariano C., and Mónica B. (2021). A Random Forest-based algorithm for data-intensive spatial interpolation in crop yield mapping.

Comput Electron Agric., 184, 106094.

Misra P. (2001). Applications of spatial statistics in agricultural surveys. Unpublished Ph.D. thesis, P.G. School, ICAR-IARI, New Delhi.

MohsenzadehKarimi S., Kisi O., Porrajabali M., Rouhani-Nia F. and Shiri J. (2020). Evaluation of the support vector machine, random forest and geo-statistical methodologies for predicting long-term air temperature. J Hydraul Eng., 26(4), 376-386.

Ohashi O. and Torgo L. (2012). Spatial interpolation using multiple regression. Proc. SIAM Int. Conf. Data Min., 2, 1044-1049.

Ozelkan E., Chen G. and Ustundag B.B. (2016). Spatial estimation of wind speed: a new integrative model using inverse distance

weighting and power law. Int. J. Digit. Earth., 9(8), 733-747.

Rai A., Gupta N.K. and Singh R. (2007). Small area estimation of crop production using spatial models. Model Assist. Stat. Appl., 2(2), 89-98.

Royall R.M. (1970). On finite population sampling theory under certain linear regression models. Biometrika, 57(2), 377-387.

Sahoo P.M., Singh R. and Rai A. (2006). Spatial sampling procedures for agricultural surveys using geographical Information system. J.

Ind. Soc. Agril. Statist, 60(2), 134-143.

Sekulic A., Kilibarda M., Heuvelink G., Nikolić M. and Bajat B. (2020). Random forest spatial interpolation. J. Remote Sens. Technol., 12(10),1687.

Sekulić A., Kilibarda M., Protić D. and Bajat B. (2021). A high resolution daily gridded meteorological dataset for Serbia made by Random Forest Spatial Interpolation. Sci. Data., 8(1), 1-12.

Singh R., Semwal D.P., Rai A. and Chhikara R.S. (2002). Small area estimation of crop yield using remote sensing satellite data. Int. J. Remote Sens., 23(1), 49.

Sud U.C., Ahmad T., Gupta V.K., Chandra H., Sahoo P.M., Aditya K. and Biswas A. (2017). Methodology for estimation of crop area

and crop yield under mixed and continuous cropping. FAO, Rome Publication., 60(2), 4-87.