Qualitative analysis of random forests for evaporation prediction in Indian Regions

Rakhee Rakhee; Archana Singh; Mamta Mittal; Amrender Kumar

doi:10.56093/ijas.v90i6.104786

Authors

Rakhee Rakhee Amity School of Engineering and Technology, Noida, Uttar Pradesh 201 303, India
Archana Singh Amity School of Engineering and Technology, Noida, Uttar Pradesh 201 303, India
Mamta Mittal Amity School of Engineering and Technology, Noida, Uttar Pradesh 201 303, India
Amrender Kumar Amity School of Engineering and Technology, Noida, Uttar Pradesh 201 303, India

https://doi.org/10.56093/ijas.v90i6.104786

Keywords:

Discriminant analysis, Logistic regression, Random forest, Sensitivity

Abstract

The performance of logistic regression, discriminant analysis, and random forest has been compared for the prediction of evaporation of different regions of India during 2019 at ICAR-IARI, New Delhi . The present experiment was performed at Raipur (Chhattisgarh), Karnal (Haryana), Pattambi (Kerala) and Anantpur (Andhra Pradesh). Evaporation and other weather parameters are collected from the year 1985-2012, 1973-2005, 1991-2005 and 1958-2010 respectively. The performance of the techniques is compared using classification, misclassification, and sensitivity of the model along with the Receiver Operating Characteristics (ROC) curve and Area Under Curve (AUC) value. The combinations of variables as independent variables are used in two sets. In the first set, maximum & minimum temperature, relative humidity morning & evening, wind speed, rainfall, and bright sunshine hours are used. In the second set mean temperature, mean relative humidity, bright sunshine hours, and wind speed is used to see the effect on evaporation. It is found that more accuracy is obtained using the second set as predictors. The model validation accuracy is checked via running developed model on out of sample data, i.e. testing data (last three years). The study demonstrates that the random forest approach predict evaporation in a much better way than logistic regression, discriminant analysis. The random forest model can provide timely information for the decision-makers to make crucial decisions impacting due to evaporation conditions in India.

Downloads

Download data is not yet available.

References

Agrawal R and Mehta S C. 2007. Weather based forecasting of crop yields, pests and diseases - IASRI models. Journal of the Indian Society of Agricultural Statistics 61(2): 255–63.

Agrawal R, Chandrahas and Aditya K. 2012. Use of discriminant function analysis for forecasting crop yield. Mausam 36(3): 455–58. DOI: https://doi.org/10.54302/mausam.v63i3.1241

Arno D C, Kristof C and Bock K W. 2018. A new Hybrid Classification algorithm for customer churn prediction based on logistic regression and decision trees. European Journal of Operational Research 269(2): 760–72. DOI: https://doi.org/10.1016/j.ejor.2018.02.009

Breiman L. 2001. Random Forests. Machine Learning 45(2): 5–32. Bhowmik A. 2009. ‘A study on logistic regression modeling for classification in agriculture’. MSc thesis, ICAR-Indian Agricultural Research Institute, New Delhi.

Baydaroglu O and Kocak K. 2014. SVR-based prediction of evaporation combined with chaotic approach. Journal of Hydrology 508(16): 356–63. DOI: https://doi.org/10.1016/j.jhydrol.2013.11.008

Benzaghta M A, Mohammed T A, Ghazali A H, Mohd A and Mohd S. 2012. Prediction of evaporation in tropical climate using artificial neural network and climate based models. Scientific Research and Essays 7(36): 3133–48. DOI: https://doi.org/10.5897/SRE11.1311

Deswal S. 2008. Modeling of evaporation using M5 model tree algorithm. Journal of Agrometeorology 10(1): 33–38. DOI: https://doi.org/10.54386/jam.v10i1.1167

Gang C, Haiguang W and Zhanhong M. 2006. Forecasting wheat stripe rust by discrimination analysis. Plant Protection 32(4): 24–27.

Kumar V, Kumar A and Chattopadhyay C. 2012. Design and implementation of web-based aphid (Lipaphis erysimi) forecast system for oilseed Brassicas. Indian Journal of Agricultural Sciences 82(7): 608–14.

Kumar A, Agrawal R and Chattopadhyay C. 2013. Weather based forecast models for diseases in mustard crop. Mausam 64(4): 663–70. DOI: https://doi.org/10.54302/mausam.v64i4.749

Kim H, Li J and Wang S. 2009. Ordinal logistic regression modelling to predict mating flights through meteorological cues. Texas A&M University, College Station, Texas. DOI: https://doi.org/10.1002/env.928

Naveen P and Seetharaman N. 1991. ‘An anlaysis of Anantpur climate, drought research seminar forum’. MSc thesis, The International Crops Research Institute for the Semi-Arid Tropics, Telangana.

Manuel D P, Angel C O, Jose A S A and Callejon A S. 2019. Logistic regression to evaluate the marketability of pepper cultivars. Agronomy 9(3): 125–43. DOI: https://doi.org/10.3390/agronomy9030125

Palmer D S, Boyle N M, Glen R C and Mitchell J B O. 2007. Random Forest models predict aqueous solubility. Journal of Chemical Information and Modeling 47(1): 150–58. DOI: https://doi.org/10.1021/ci060164k

R Development Core Team. R: A language and environment for statistical computing, URL http://www.R-project.org (accessed Sept 06, 2019).

Sahu S, Chawla M and Khare N. 2017. An efficient analysis of crop yield prediction using Hadoop framework based on random forest approach. (In) Proceeding of International Conference Computing, Communication and Automation (ICCCA), Greater Noida, India, May 5-6, pp. 53–57. DOI: https://doi.org/10.1109/CCAA.2017.8229770

Zibaei M and Bakhshoodeh M. 2008. Investigating determinants of sprinkler irrigation technology discontinuance in Iran: Comparison of logistic regression and discriminant analysis. Journal of Agricultural and Environmental Sciences 22(5): 46–55.