Prediction of bean production and yields, with artificial neural network models and climate data
The state of Zacatecas ranks first in the production of rainfed beans in Mexico. Due to the economic and food security repercussions, it is important to predict yields, production and harvested area, as well as to know the climatological variables that have the greatest effect on bean cultivation. T...
Сохранить в:
| Главные авторы: | , , , , |
|---|---|
| Формат: | Online |
| Язык: | spa |
| Опубликовано: |
Universidad de Sonora
2022
|
| Online-ссылка: | https://biotecnia.unison.mx/index.php/biotecnia/article/view/1664 |
| Метки: |
Добавить метку
Нет меток, Требуется 1-ая метка записи!
|
| id |
biotecnia-article-1664 |
|---|---|
| record_format |
ojs |
| institution |
Biotecnia |
| collection |
OJS |
| language |
spa |
| format |
Online |
| author |
Servín-Palestina, Miguel Salazar-Moreno, Raquel López-Cruz, Irineo Medina-García, Guillermo Cid-Ríos, José Ángel |
| spellingShingle |
Servín-Palestina, Miguel Salazar-Moreno, Raquel López-Cruz, Irineo Medina-García, Guillermo Cid-Ríos, José Ángel Prediction of bean production and yields, with artificial neural network models and climate data |
| author_facet |
Servín-Palestina, Miguel Salazar-Moreno, Raquel López-Cruz, Irineo Medina-García, Guillermo Cid-Ríos, José Ángel |
| author_sort |
Servín-Palestina, Miguel |
| title |
Prediction of bean production and yields, with artificial neural network models and climate data |
| title_short |
Prediction of bean production and yields, with artificial neural network models and climate data |
| title_full |
Prediction of bean production and yields, with artificial neural network models and climate data |
| title_fullStr |
Prediction of bean production and yields, with artificial neural network models and climate data |
| title_full_unstemmed |
Prediction of bean production and yields, with artificial neural network models and climate data |
| title_sort |
prediction of bean production and yields, with artificial neural network models and climate data |
| description |
The state of Zacatecas ranks first in the production of rainfed beans in Mexico. Due to the economic and food security repercussions, it is important to predict yields, production and harvested area, as well as to know the climatological variables that have the greatest effect on bean cultivation. The objectives of the present work were 1) to develop ANN models for the prediction of the harvested area, yields and production of rainfed beans in the state of Zacatecas, using data on maximum and minimum air temperature, precipitation and evaporation during the period 1988-2019. 2) to determine the input variables that have the greatest influence on bean production and yield through sensitivity analysis. Due to the limited availability of climatic data, the Climatol library of the R statistical package was used to fill in missing data. The results show that the RNA models capture the influence of climate on bean production, with an overall efficiency of 0.89 for Rto and 0.86 for SC. The production was estimated using the outputs, Rto and SC, from RNA models and an R2 =0.80 was obtained. According to the sensitivity analysis, Evaporation of the cycle is the most important variable in predicting yield, while precipitation in August (Pp_Ago) and minimum temperature (Tmin) had a greater influence on production.
|
| publisher |
Universidad de Sonora |
| publishDate |
2022 |
| url |
https://biotecnia.unison.mx/index.php/biotecnia/article/view/1664 |
| work_keys_str_mv |
AT servinpalestinamiguel predictionofbeanproductionandyieldswithartificialneuralnetworkmodelsandclimatedata AT salazarmorenoraquel predictionofbeanproductionandyieldswithartificialneuralnetworkmodelsandclimatedata AT lopezcruzirineo predictionofbeanproductionandyieldswithartificialneuralnetworkmodelsandclimatedata AT medinagarciaguillermo predictionofbeanproductionandyieldswithartificialneuralnetworkmodelsandclimatedata AT cidriosjoseangel predictionofbeanproductionandyieldswithartificialneuralnetworkmodelsandclimatedata AT servinpalestinamiguel predicciondelaproduccionyrendimientodefrijolconmodelosderedesneuronalesartificialesydatosclimaticos AT salazarmorenoraquel predicciondelaproduccionyrendimientodefrijolconmodelosderedesneuronalesartificialesydatosclimaticos AT lopezcruzirineo predicciondelaproduccionyrendimientodefrijolconmodelosderedesneuronalesartificialesydatosclimaticos AT medinagarciaguillermo predicciondelaproduccionyrendimientodefrijolconmodelosderedesneuronalesartificialesydatosclimaticos AT cidriosjoseangel predicciondelaproduccionyrendimientodefrijolconmodelosderedesneuronalesartificialesydatosclimaticos |
| _version_ |
1764647735331389440 |
| spelling |
biotecnia-article-16642022-12-16T18:55:16Z Prediction of bean production and yields, with artificial neural network models and climate data Predicción de la producción y rendimiento de frijol, con modelos de redes neuronales artificiales y datos climáticos Servín-Palestina, Miguel Salazar-Moreno, Raquel López-Cruz, Irineo Medina-García, Guillermo Cid-Ríos, José Ángel Inteligencia artificial, Zacatecas, temperatura, precipitación, cultivos de temporal, Phaseolus vulgaris, L artificial intelligence Zacatecas temperature rainfall rainfed crops Phaseolus vulgaris L. The state of Zacatecas ranks first in the production of rainfed beans in Mexico. Due to the economic and food security repercussions, it is important to predict yields, production and harvested area, as well as to know the climatological variables that have the greatest effect on bean cultivation. The objectives of the present work were 1) to develop ANN models for the prediction of the harvested area, yields and production of rainfed beans in the state of Zacatecas, using data on maximum and minimum air temperature, precipitation and evaporation during the period 1988-2019. 2) to determine the input variables that have the greatest influence on bean production and yield through sensitivity analysis. Due to the limited availability of climatic data, the Climatol library of the R statistical package was used to fill in missing data. The results show that the RNA models capture the influence of climate on bean production, with an overall efficiency of 0.89 for Rto and 0.86 for SC. The production was estimated using the outputs, Rto and SC, from RNA models and an R2 =0.80 was obtained. According to the sensitivity analysis, Evaporation of the cycle is the most important variable in predicting yield, while precipitation in August (Pp_Ago) and minimum temperature (Tmin) had a greater influence on production. El estado de Zacatecas ocupa el primer lugar en la producción de frijol de temporal en México. Debido a las repercusiones económicas y de seguridad alimentaria, es importante la predicción de los rendimientos, producción y superficie cosechada, igualmente, conocer las variables climatológicas que mayor efecto tienen en el cultivo de frijol. Los objetivos del presente trabajo fueron 1) desarrollar modelos de redes neuronales artificiales RNA para la predicción de la superficie cosechada (SC), los rendimientos (Rto) y la producción (P) de frijol de temporal en el estado de Zacatecas, empleando datos de temperatura máxima y mínima del aire, precipitación y evaporación durante el periodo 1988-2019. 2) realizar un análisis de sensibilidad para determinar las variables de entrada que tienen mayor influencia en la producción y rendimiento de frijol. Debido a la limitada disponibilidad de datos climáticos, se usó la librería Climatol del paquete estadístico R, para el llenado de datos faltantes. Los resultados muestran que los modelos de RNA son capaces de detectar la influencia del clima en la producción de frijol. La eficiencia global en los modelos RNA fue de 0.89 para Rto y 0.86 para SC. La producción se estimó con los modelos de RNA para Rto y SC y se obtuvo un R2 =0.80. De acuerdo al análisis de sensibilidad, la evaporación del ciclo del cultivo (Eva) es la variable más importante en la predicción del rendimiento, mientras que la precipitación de agosto (Pp_Ago) y la temperatura mínima (Tmin) influyeron más en la producción. Universidad de Sonora 2022-05-31 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Original peer-reviewed articles Artículos originales evaluados por pares application/pdf text/xml https://biotecnia.unison.mx/index.php/biotecnia/article/view/1664 10.18633/biotecnia.v24i2.1664 Biotecnia; Vol. 24 No. 2 (2022): Mayo-Agosto; 104-111 Biotecnia; Vol. 24 Núm. 2 (2022): Mayo-Agosto; 104-111 1665-1456 1665-1456 spa https://biotecnia.unison.mx/index.php/biotecnia/article/view/1664/658 https://biotecnia.unison.mx/index.php/biotecnia/article/view/1664/761 Derechos de autor 2022 https://creativecommons.org/licenses/by-nc-sa/4.0 |
