Untangling the effect of soil quality on rice productivity under a 16-years long-term fertilizer experiment using conditional random forest

In a 16-years long-term fertilizer experiment, an in-depth study was carried out to evaluate the changes in soil physical, chemical, and biological properties under long-term fertilizer application and establish cause and effect relationship between soil properties and rice productivity using interp...

Descripción completa

Detalles Bibliográficos
Autores principales: Garnaik, Saheed, Samant, Prasanna Kumar, Mandal, Mitali, Mohanty, Tushar Ranjan, Dwibedi, Sanat Kumar, Patra, Ranjan Kumar, Mohapatra, Kiran Kumar, Wanjari, Ravi H., Sethi, Debadatta, Sena, Dipaka Ranjan, Sapkota, Tek Bahadur, Nayak, Jagmohan, Patra, Sridhar, Parihar, Chiter Mal, Nayak, Harisankar
Formato: Journal Article
Lenguaje:Inglés
Publicado: Elsevier 2022
Materias:
Acceso en línea:https://hdl.handle.net/10568/128392
_version_ 1855522436963893248
author Garnaik, Saheed
Samant, Prasanna Kumar
Mandal, Mitali
Mohanty, Tushar Ranjan
Dwibedi, Sanat Kumar
Patra, Ranjan Kumar
Mohapatra, Kiran Kumar
Wanjari, Ravi H.
Sethi, Debadatta
Sena, Dipaka Ranjan
Sapkota, Tek Bahadur
Nayak, Jagmohan
Patra, Sridhar
Parihar, Chiter Mal
Nayak, Harisankar
author_browse Dwibedi, Sanat Kumar
Garnaik, Saheed
Mandal, Mitali
Mohanty, Tushar Ranjan
Mohapatra, Kiran Kumar
Nayak, Harisankar
Nayak, Jagmohan
Parihar, Chiter Mal
Patra, Ranjan Kumar
Patra, Sridhar
Samant, Prasanna Kumar
Sapkota, Tek Bahadur
Sena, Dipaka Ranjan
Sethi, Debadatta
Wanjari, Ravi H.
author_facet Garnaik, Saheed
Samant, Prasanna Kumar
Mandal, Mitali
Mohanty, Tushar Ranjan
Dwibedi, Sanat Kumar
Patra, Ranjan Kumar
Mohapatra, Kiran Kumar
Wanjari, Ravi H.
Sethi, Debadatta
Sena, Dipaka Ranjan
Sapkota, Tek Bahadur
Nayak, Jagmohan
Patra, Sridhar
Parihar, Chiter Mal
Nayak, Harisankar
author_sort Garnaik, Saheed
collection Repository of Agricultural Research Outputs (CGSpace)
description In a 16-years long-term fertilizer experiment, an in-depth study was carried out to evaluate the changes in soil physical, chemical, and biological properties under long-term fertilizer application and establish cause and effect relationship between soil properties and rice productivity using interpretable machine learning. There were 12 treatments involving control (without fertilizer application), 100% N (recommended dose of nitrogen), 100% NP (recommended dose of nitrogen and phosphorus), 100% PK (recommended dose of phosphorus and potassium), 100% NPK (recommended dose of nitrogen, phosphorus, and potassium), 150% NPK (50% higher nitrogen, phosphorus, and potassium than recommended), 100% NPK + Zn (recommended nitrogen, phosphorus, and potassium along with Zinc), 100% NPK + FYM (recommended nitrogen, phosphorus, and potassium along with farmyard manure (FYM)), 100% NPK + FYM + LIME (recommended nitrogen, phosphorus, and potassium along with FYM and lime), 100% NPK + Zn + S (recommended nitrogen, phosphorus, and potassium along with zinc and sulphur), 100% NPK + Zn + B (recommended nitrogen, phosphorus, and potassium along with Zinc and Boron) and 100% NPK + Lime (recommended nitrogen, phosphorus, and potassium along with lime). At first, a conditional random forest model was built, based on which important variables were selected using the permutation-based variable importance approach. Further, the accumulated local effect plot was used to establish a cause and effect relationship between important soil properties and rice yield. Although most of the soil properties varied across the treatments, total potassium, protease, urease, and permanganate oxidisable carbon are the most important soil properties, individually accounting for up to 400 kg ha−1 variation in the rice productivity. The study demonstrated how interpretable machine learning techniques could be used in long-term fertilizer experiments to unravel the most meaningful information, and these techniques can be used in other similar long-term experiments.
format Journal Article
id CGSpace128392
institution CGIAR Consortium
language Inglés
publishDate 2022
publishDateRange 2022
publishDateSort 2022
publisher Elsevier
publisherStr Elsevier
record_format dspace
spelling CGSpace1283922025-12-08T09:54:28Z Untangling the effect of soil quality on rice productivity under a 16-years long-term fertilizer experiment using conditional random forest Garnaik, Saheed Samant, Prasanna Kumar Mandal, Mitali Mohanty, Tushar Ranjan Dwibedi, Sanat Kumar Patra, Ranjan Kumar Mohapatra, Kiran Kumar Wanjari, Ravi H. Sethi, Debadatta Sena, Dipaka Ranjan Sapkota, Tek Bahadur Nayak, Jagmohan Patra, Sridhar Parihar, Chiter Mal Nayak, Harisankar machine learning parcels soil properties rice fertilizers In a 16-years long-term fertilizer experiment, an in-depth study was carried out to evaluate the changes in soil physical, chemical, and biological properties under long-term fertilizer application and establish cause and effect relationship between soil properties and rice productivity using interpretable machine learning. There were 12 treatments involving control (without fertilizer application), 100% N (recommended dose of nitrogen), 100% NP (recommended dose of nitrogen and phosphorus), 100% PK (recommended dose of phosphorus and potassium), 100% NPK (recommended dose of nitrogen, phosphorus, and potassium), 150% NPK (50% higher nitrogen, phosphorus, and potassium than recommended), 100% NPK + Zn (recommended nitrogen, phosphorus, and potassium along with Zinc), 100% NPK + FYM (recommended nitrogen, phosphorus, and potassium along with farmyard manure (FYM)), 100% NPK + FYM + LIME (recommended nitrogen, phosphorus, and potassium along with FYM and lime), 100% NPK + Zn + S (recommended nitrogen, phosphorus, and potassium along with zinc and sulphur), 100% NPK + Zn + B (recommended nitrogen, phosphorus, and potassium along with Zinc and Boron) and 100% NPK + Lime (recommended nitrogen, phosphorus, and potassium along with lime). At first, a conditional random forest model was built, based on which important variables were selected using the permutation-based variable importance approach. Further, the accumulated local effect plot was used to establish a cause and effect relationship between important soil properties and rice yield. Although most of the soil properties varied across the treatments, total potassium, protease, urease, and permanganate oxidisable carbon are the most important soil properties, individually accounting for up to 400 kg ha−1 variation in the rice productivity. The study demonstrated how interpretable machine learning techniques could be used in long-term fertilizer experiments to unravel the most meaningful information, and these techniques can be used in other similar long-term experiments. 2022-06 2023-02-02T11:10:40Z 2023-02-02T11:10:40Z Journal Article https://hdl.handle.net/10568/128392 en Limited Access Elsevier Garnaik, S., Samant, P.K., Mandal, M., Mohanty, T.R., Dwibedi, S.K., Patra, R.K., Mohapatra, K.K., Wanjari, R.H., Sethi, D., Sena, D.R., Sapkota, T.B., Nayak, J., Patra, S., Parihar, C. M. and Nayak, H.S. 2022. Untangling the effect of soil quality on rice productivity under a 16-years long-term fertilizer experiment using conditional random forest. Computers and Electronics in Agriculture 197:106965.
spellingShingle machine learning
parcels
soil properties
rice
fertilizers
Garnaik, Saheed
Samant, Prasanna Kumar
Mandal, Mitali
Mohanty, Tushar Ranjan
Dwibedi, Sanat Kumar
Patra, Ranjan Kumar
Mohapatra, Kiran Kumar
Wanjari, Ravi H.
Sethi, Debadatta
Sena, Dipaka Ranjan
Sapkota, Tek Bahadur
Nayak, Jagmohan
Patra, Sridhar
Parihar, Chiter Mal
Nayak, Harisankar
Untangling the effect of soil quality on rice productivity under a 16-years long-term fertilizer experiment using conditional random forest
title Untangling the effect of soil quality on rice productivity under a 16-years long-term fertilizer experiment using conditional random forest
title_full Untangling the effect of soil quality on rice productivity under a 16-years long-term fertilizer experiment using conditional random forest
title_fullStr Untangling the effect of soil quality on rice productivity under a 16-years long-term fertilizer experiment using conditional random forest
title_full_unstemmed Untangling the effect of soil quality on rice productivity under a 16-years long-term fertilizer experiment using conditional random forest
title_short Untangling the effect of soil quality on rice productivity under a 16-years long-term fertilizer experiment using conditional random forest
title_sort untangling the effect of soil quality on rice productivity under a 16 years long term fertilizer experiment using conditional random forest
topic machine learning
parcels
soil properties
rice
fertilizers
url https://hdl.handle.net/10568/128392
work_keys_str_mv AT garnaiksaheed untanglingtheeffectofsoilqualityonriceproductivityundera16yearslongtermfertilizerexperimentusingconditionalrandomforest
AT samantprasannakumar untanglingtheeffectofsoilqualityonriceproductivityundera16yearslongtermfertilizerexperimentusingconditionalrandomforest
AT mandalmitali untanglingtheeffectofsoilqualityonriceproductivityundera16yearslongtermfertilizerexperimentusingconditionalrandomforest
AT mohantytusharranjan untanglingtheeffectofsoilqualityonriceproductivityundera16yearslongtermfertilizerexperimentusingconditionalrandomforest
AT dwibedisanatkumar untanglingtheeffectofsoilqualityonriceproductivityundera16yearslongtermfertilizerexperimentusingconditionalrandomforest
AT patraranjankumar untanglingtheeffectofsoilqualityonriceproductivityundera16yearslongtermfertilizerexperimentusingconditionalrandomforest
AT mohapatrakirankumar untanglingtheeffectofsoilqualityonriceproductivityundera16yearslongtermfertilizerexperimentusingconditionalrandomforest
AT wanjariravih untanglingtheeffectofsoilqualityonriceproductivityundera16yearslongtermfertilizerexperimentusingconditionalrandomforest
AT sethidebadatta untanglingtheeffectofsoilqualityonriceproductivityundera16yearslongtermfertilizerexperimentusingconditionalrandomforest
AT senadipakaranjan untanglingtheeffectofsoilqualityonriceproductivityundera16yearslongtermfertilizerexperimentusingconditionalrandomforest
AT sapkotatekbahadur untanglingtheeffectofsoilqualityonriceproductivityundera16yearslongtermfertilizerexperimentusingconditionalrandomforest
AT nayakjagmohan untanglingtheeffectofsoilqualityonriceproductivityundera16yearslongtermfertilizerexperimentusingconditionalrandomforest
AT patrasridhar untanglingtheeffectofsoilqualityonriceproductivityundera16yearslongtermfertilizerexperimentusingconditionalrandomforest
AT pariharchitermal untanglingtheeffectofsoilqualityonriceproductivityundera16yearslongtermfertilizerexperimentusingconditionalrandomforest
AT nayakharisankar untanglingtheeffectofsoilqualityonriceproductivityundera16yearslongtermfertilizerexperimentusingconditionalrandomforest