Interpretable machine learning methods to explain on-farm yield variability of high productivity wheat in Northwest India (Record no. 65433)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 05426nab|a22004817a|4500 |
| 001 - CONTROL NUMBER | |
| control field | 65433 |
| 003 - CONTROL NUMBER IDENTIFIER | |
| control field | MX-TxCIM |
| 005 - DATE AND TIME OF LATEST TRANSACTION | |
| control field | 20240919020919.0 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION | |
| fixed length control field | 22082922022|||mne ||p|op||||00||0|eengdd |
| 022 ## - INTERNATIONAL STANDARD SERIAL NUMBER | |
| International Standard Serial Number | 0378-4290 |
| 022 ## - INTERNATIONAL STANDARD SERIAL NUMBER | |
| International Standard Serial Number | 1872-6852 (Online) |
| 024 ## - OTHER STANDARD IDENTIFIER | |
| Source of number or code | https://doi.org/10.1016/j.fcr.2022.108640 |
| 040 ## - CATALOGING SOURCE | |
| Original cataloging agency | MX-TxCIM |
| 041 ## - LANGUAGE CODE | |
| Language code of text/sound track or separate title | eng |
| 100 0# - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Hari S. Nayak |
| 9 (RLIN) | 8233 |
| 245 10 - TITLE STATEMENT | |
| Title | Interpretable machine learning methods to explain on-farm yield variability of high productivity wheat in Northwest India |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. (IMPRINT) | |
| Name of publisher, distributor, etc. | Elsevier, |
| Date of publication, distribution, etc. | 2022. |
| Place of publication, distribution, etc. | Amsterdam (Netherlands) : |
| 500 ## - GENERAL NOTE | |
| General note | Peer review |
| 500 ## - GENERAL NOTE | |
| General note | Open Access |
| 520 ## - SUMMARY, ETC. | |
| Summary, etc. | The increasing availability of complex, geo-referenced on-farm data demands analytical frameworks that can guide crop management recommendations. Recent developments in interpretable machine learning techniques offer opportunities to use these methods in agronomic studies. Our objectives were two-fold: (1) to assess the performance of different machine learning methods to explain on-farm wheat yield variability in the Northwestern Indo-Gangetic Plains of India, and (2) to identify the most important drivers and interactions explaining wheat yield variability. A suite of fine-tuned machine learning models (ridge and lasso regression, classification and regression trees, k-nearest neighbor, support vector machines, gradient boosting, extreme gradient boosting, and random forest) were statistically compared using the R2, root mean square error (RMSE), and mean absolute error (MAE). The best performing model was again fine-tuned using a grid search approach for the bias-variance trade-off. Three post-hoc model agnostic techniques were used to interpret the best performing model: variable importance (a variable was considered “important” if shuffling its values increased or decreased the model error considerably), interaction strength (based on Friedman’s H-statistic), and two-way interaction (i.e., how much of the total variability in wheat yield was explained by a particular two-way interaction). Model outputs were compared against empirical data to contextualize results and provide a blueprint for future analysis in other production systems. Tree-based and decision boundary-based methods outperformed regression-based methods in explaining wheat yield variability. Random forest was the best performing method in terms of goodness-of-fit and model precision and accuracy with RMSE, MAE, and R2 ranging between 367 and 470 kg ha−1, 276–345 kg ha−1, and 0.44–0.63, respectively. Random forest was then used for selection of important variables and interactions. The most important management variables explaining wheat yield variability were nitrogen application rate and crop residue management, whereas the average of monthly cumulative solar radiation during February and March (coinciding with reproductive phase of wheat) was the most important biophysical variable. The effect size of these variables on wheat yield ranged between 227 kg ha−1 for nitrogen application rate to 372 kg ha−1 for cumulative solar radiation during February and March. The effect of important interactions on wheat yield was detected in the data namely the interaction between crop residue management and disease management and, nitrogen application rate and seeding rate. For instance, farmers’ fields with moderate disease incidence yielded 750 kg ha−1 less when crop residues were removed than when crop residues were retained. Similarly, wheat yield response to residue retention was higher under low seed and N application rates. As an inductive research approach, the appropriate application of interpretable machine learning methods can be used to extract agronomically actionable information from large-scale farmer field data. |
| 546 ## - LANGUAGE NOTE | |
| Language note | Text in English |
| 591 ## - CATALOGING NOTES | |
| Affiliation | Kakraliya Suresh Kumar : Not in IRS staff list but CIMMYT Affiliation |
| 597 ## - CGIAR Initiative | |
| CGIAR Impact area | Nutrition, health & food security |
| CGIAR Initiative | Transforming Agrifood Systems in South Asia |
| CGIAR Action areas | Resilient Agrifood Systems |
| Donor or Funder | |
| -- | CGIAR Trust Fund |
| -- | |
| CGSpace handle | https://hdl.handle.net/10568/127194 |
| 650 #7 - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Source of heading or term | AGROVOC |
| 9 (RLIN) | 5702 |
| Topical term or geographic name as entry element | Forests |
| 650 #7 - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Source of heading or term | AGROVOC |
| 9 (RLIN) | 11127 |
| Topical term or geographic name as entry element | Machine learning |
| 650 #7 - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Source of heading or term | AGROVOC |
| 9 (RLIN) | 1310 |
| Topical term or geographic name as entry element | Wheat |
| 650 #7 - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Source of heading or term | AGROVOC |
| 9 (RLIN) | 1313 |
| Topical term or geographic name as entry element | Yields |
| 650 #7 - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Source of heading or term | AGROVOC |
| 9 (RLIN) | 1064 |
| Topical term or geographic name as entry element | Crop residues |
| 651 #7 - SUBJECT ADDED ENTRY--GEOGRAPHIC NAME | |
| Source of heading or term | AGROVOC |
| 9 (RLIN) | 3726 |
| Geographic name | India |
| 700 1# - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Silva, J.V. |
| Field link and sequence number | 001712458 |
| Miscellaneous information | Sustainable Intensification Program |
| -- | Sustainable Agrifood Systems |
| 9 (RLIN) | 9320 |
| 700 1# - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Parihar, C.M. |
| 9 (RLIN) | 1486 |
| 700 1# - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Krupnik, T.J. |
| Miscellaneous information | Sustainable Intensification Program |
| -- | Sustainable Agrifood Systems |
| Field link and sequence number | INT3222 |
| 9 (RLIN) | 906 |
| 700 1# - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Sena, D.R. |
| 9 (RLIN) | 4051 |
| 700 0# - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Kakraliya Suresh Kumar |
| 9 (RLIN) | 6321 |
| 700 1# - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Jat, H.S. |
| 9 (RLIN) | 5697 |
| 700 1# - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Sidhu, H.S. |
| Miscellaneous information | Formerly Borlaug Institute for South Asia |
| Field link and sequence number | INT3482 |
| 9 (RLIN) | 961 |
| 700 1# - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Sharma, P.C. |
| 9 (RLIN) | 2439 |
| 700 1# - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Jat, M.L. |
| Miscellaneous information | Formerly Sustainable Intensification Program |
| -- | Formerly Sustainable Agrifood Systems |
| Field link and sequence number | INT3072 |
| 9 (RLIN) | 889 |
| 700 1# - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Sapkota, T.B. |
| Miscellaneous information | Sustainable Intensification Program |
| -- | Sustainable Agrifood Systems |
| Field link and sequence number | INT3361 |
| 9 (RLIN) | 940 |
| 773 0# - HOST ITEM ENTRY | |
| Title | Field Crops Research |
| Related parts | v. 287, art. 108640 |
| Place, publisher, and date of publication | Amsterdam (Netherlands) : Elsevier, 2022. |
| Record control number | G444314 |
| International Standard Serial Number | 0378-4290 |
| 856 ## - ELECTRONIC LOCATION AND ACCESS | |
| Link text | Open Access through DSpace |
| Uniform Resource Identifier | https://hdl.handle.net/10883/22163 |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Koha item type | Article |
| Suppress in OPAC | No |
| Source of classification or shelving scheme | Dewey Decimal Classification |
| Date last seen | Total Checkouts | Price effective from | Koha item type | Lost status | Source of classification or shelving scheme | Damaged status | Not for loan | Collection code | Withdrawn status | Home library | Current library | Date acquired |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 07/08/2022 | 07/08/2022 | Article | Not Lost | Dewey Decimal Classification | CIMMYT Staff Publications Collection | CIMMYT Knowledge Center: John Woolston Library | CIMMYT Knowledge Center: John Woolston Library | 07/08/2022 |