Green gram yield prediction using linear regression
Predicting crop yields before harvest is key in enabling farmers make critical decisions as far as postharvest management is concerned. Besides, yield prediction plays a critical role in agriculture enterprise selection hence promoting food and nutrition security in a community. It is worth noting t...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
African Journal of Rural Development
2025
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/20.500.12493/2868 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823844184207917056 |
|---|---|
| author | Tumusiime, Robert Mabirizi, Vicent Mirembe, D.P Arinanye, T.R |
| author_facet | Tumusiime, Robert Mabirizi, Vicent Mirembe, D.P Arinanye, T.R |
| author_sort | Tumusiime, Robert |
| collection | KAB-DR |
| description | Predicting crop yields before harvest is key in enabling farmers make critical decisions as far as postharvest management is concerned. Besides, yield prediction plays a critical role in agriculture enterprise selection hence promoting food and nutrition security in a community. It is worth noting that various factors including ecological zones characteristics and farm management practices can vary significantly from season to season and farm to farmer, hence affecting crop yields. Given the importance of crop yield prediction in agriculture enterprise development and investments, a number of approaches have been adopted by farmers and breeders alike. These approaches range from controlled ideal condition analysis by breeders to the use of advanced plant physiological feature analysis using satellite image processing techniques. While a number of popular crops like rice and maize have a number of models proposed, limited yield prediction studies have been done on neglected crops like green gram. Therefore, this paper discusses the proposed green gram crop yield prediction model based on a stepwise linear regression technique using ecological zone characteristics, farm management practices and historic crop yield as the key variables. The study used a dataset of 107 records (gardens) and 9 features obtained from National Semi-Arid Research Institute (NaSARRI), Serere, Uganda. The predictor variables used were; soil type, soil PH, soil fertility, rainfall distribution, weeding practice, pest and disease management, fertilizer application, plant spacing, and cropping system. The model was evaluated for precision and evaluation result revealed that, with a mean absolute percentage error (MAPE) of 16.8%, the proposed model had a precision of 96.4% was deemed accurate in predicting green gram yield. |
| format | Article |
| id | oai:idr.kab.ac.ug:20.500.12493-2868 |
| institution | KAB-DR |
| language | English |
| publishDate | 2025 |
| publisher | African Journal of Rural Development |
| record_format | dspace |
| spelling | oai:idr.kab.ac.ug:20.500.12493-28682025-02-05T00:00:45Z Green gram yield prediction using linear regression Tumusiime, Robert Mabirizi, Vicent Mirembe, D.P Arinanye, T.R Crop yields Green gram linear regression Prediction models Uganda Predicting crop yields before harvest is key in enabling farmers make critical decisions as far as postharvest management is concerned. Besides, yield prediction plays a critical role in agriculture enterprise selection hence promoting food and nutrition security in a community. It is worth noting that various factors including ecological zones characteristics and farm management practices can vary significantly from season to season and farm to farmer, hence affecting crop yields. Given the importance of crop yield prediction in agriculture enterprise development and investments, a number of approaches have been adopted by farmers and breeders alike. These approaches range from controlled ideal condition analysis by breeders to the use of advanced plant physiological feature analysis using satellite image processing techniques. While a number of popular crops like rice and maize have a number of models proposed, limited yield prediction studies have been done on neglected crops like green gram. Therefore, this paper discusses the proposed green gram crop yield prediction model based on a stepwise linear regression technique using ecological zone characteristics, farm management practices and historic crop yield as the key variables. The study used a dataset of 107 records (gardens) and 9 features obtained from National Semi-Arid Research Institute (NaSARRI), Serere, Uganda. The predictor variables used were; soil type, soil PH, soil fertility, rainfall distribution, weeding practice, pest and disease management, fertilizer application, plant spacing, and cropping system. The model was evaluated for precision and evaluation result revealed that, with a mean absolute percentage error (MAPE) of 16.8%, the proposed model had a precision of 96.4% was deemed accurate in predicting green gram yield. 2025-02-04T12:40:01Z 2025-02-04T12:40:01Z 2025 Article Tumusiime, R., Mabirizi, V., Mirembe, D. P., Arinanye, T.R. and Lubega, J. (2025). Green gram yield prediction using linear regression. African Journal of Rural Development 9 (2):149-163. 2415-2838 http://hdl.handle.net/20.500.12493/2868 en Attribution-NonCommercial-NoDerivs 3.0 United States http://creativecommons.org/licenses/by-nc-nd/3.0/us/ application/pdf African Journal of Rural Development |
| spellingShingle | Crop yields Green gram linear regression Prediction models Uganda Tumusiime, Robert Mabirizi, Vicent Mirembe, D.P Arinanye, T.R Green gram yield prediction using linear regression |
| title | Green gram yield prediction using linear regression |
| title_full | Green gram yield prediction using linear regression |
| title_fullStr | Green gram yield prediction using linear regression |
| title_full_unstemmed | Green gram yield prediction using linear regression |
| title_short | Green gram yield prediction using linear regression |
| title_sort | green gram yield prediction using linear regression |
| topic | Crop yields Green gram linear regression Prediction models Uganda |
| url | http://hdl.handle.net/20.500.12493/2868 |
| work_keys_str_mv | AT tumusiimerobert greengramyieldpredictionusinglinearregression AT mabirizivicent greengramyieldpredictionusinglinearregression AT mirembedp greengramyieldpredictionusinglinearregression AT arinanyetr greengramyieldpredictionusinglinearregression |