Big data, small explanatory and predictive power: Lessons from random forest modeling of on-farm yield variability and implications for data-driven agronomy

Martin van Ittersum (2023, [Artículo])

Context: Collection and analysis of large volumes of on-farm production data are widely seen as key to understanding yield variability among farmers and improving resource-use efficiency. Objective: The aim of this study was to assess the performance of statistical and machine learning methods to explain and predict crop yield across thousands of farmers’ fields in contrasting farming systems worldwide. Methods: A large database of 10,940 field-year combinations from three countries in different stages of agricultural intensification was analyzed. Random effects models were used to partition crop yield variability and random forest models were used to explain and predict crop yield within a cross-validation scheme with data re-sampling over space and time. Results: Yield variability in relative terms was smallest for wheat and barley in the Netherlands and for wheat in Ethiopia, intermediate for rice in the Philippines, and greatest for maize in Ethiopia. Random forest models comprising a total of 87 variables explained a maximum of 65 % of cereal yield variability in the Netherlands and less than 45 % of cereal yield variability in Ethiopia and in the Philippines. Crop management related variables were important to explain and predict cereal yields in Ethiopia, while predictive (i.e., known before the growing season) climatic variables and explanatory (i.e., known during or after the growing season) climatic variables were most important to explain and predict cereal yield variability in the Philippines and in the Netherlands, respectively. Finally, model cross-validation for regions or years not seen during model training reduced the R2 considerably for most crop x country combinations, while for wheat in the Netherlands this was model dependent. Conclusion: Big data from farmers’ fields is useful to explain on-farm yield variability to some extent, but not to predict it across time and space. Significance: The results call for moderate expectations towards big data and machine learning in agronomic studies, particularly for smallholder farms in the tropics where model performance was poorest independently of the variables considered and the cross-validation scheme used.

Model Accuracy Model Precision Linear Mixed Models CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA MACHINE LEARNING SUSTAINABLE INTENSIFICATION BIG DATA YIELDS MODELS AGRONOMY

Using an incomplete block design to allocate lines to environments improves sparse genome-based prediction in plant breeding

Osval Antonio Montesinos-Lopez ABELARDO MONTESINOS LOPEZ RICARDO ACOSTA DIAZ Rajeev Varshney Jose Crossa ALISON BENTLEY (2022, [Artículo])

Genomic selection (GS) is a predictive methodology that trains statistical machine-learning models with a reference population that is used to perform genome-enabled predictions of new lines. In plant breeding, it has the potential to increase the speed and reduce the cost of selection. However, to optimize resources, sparse testing methods have been proposed. A common approach is to guarantee a proportion of nonoverlapping and overlapping lines allocated randomly in locations, that is, lines appearing in some locations but not in all. In this study we propose using incomplete block designs (IBD), principally, for the allocation of lines to locations in such a way that not all lines are observed in all locations. We compare this allocation with a random allocation of lines to locations guaranteeing that the lines are allocated to

the same number of locations as under the IBD design. We implemented this benchmarking on several crop data sets under the Bayesian genomic best linear unbiased predictor (GBLUP) model, finding that allocation under the principle of IBD outperformed random allocation by between 1.4% and 26.5% across locations, traits, and data sets in terms of mean square error. Although a wide range of performance improvements were observed, our results provide evidence that using IBD for the allocation of lines to locations can help improve predictive performance compared with random allocation. This has the potential to be applied to large-scale plant breeding programs.

CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA Bayes Theorem Genome Inflammatory Bowel Diseases Models, Genetic Plant Breeding

Energy and economic efficiency of climate-smart agriculture practices in a rice–wheat cropping system of India

Manish Kakraliya Deepak Bijarniya Parbodh Chander Sharma ML JAT (2022, [Artículo])

Intensive Tillage Conventional Rice–Wheat Systems Energy Efficiency On-Farm Studies Climate-Smart Agricultural Practices CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA CLIMATE-SMART AGRICULTURE RICE WHEAT CROPPING SYSTEMS

Low nitrogen narrows down phenotypic diversity in durum wheat

Tesfaye Geleta Aga Bekele Abeyo (2023, [Artículo])

Clusters Durum Wheat Nitrogen Efficiency CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA HARD WHEAT GENETIC DIVERGENCE NORMALIZED DIFFERENCE VEGETATION INDEX NITROGEN PRINCIPAL COMPONENT ANALYSIS

Agricultural emissions reduction potential by improving technical efficiency in crop production

Arun Khatri-Chhetri Tek Sapkota sofina maharjan Paresh Shirsath (2023, [Artículo])

CONTEXT: Global and national agricultural development policies normally tend to focus more on enhancing farm productivity through technological changes than on better use of existing technologies. The role of improving technical efficiency in greenhouse gas (GHG) emissions reduction from crop production is the least explored area in the agricultural sector. But improving technical efficiency is necessary in the context of the limited availability of existing natural resources (particularly land and water) and the need for GHG emission reduction from the agriculture sector. Technical efficiency gains in the production process are linked with the amount of input used nd the cost of production that determines both economic and environmental gains from the better use of existing technologies. OBJECTIVE: To assess a relationship between technical efficiency and GHG emissions and test the hypothesis that improving technical efficiency reduces GHG emissions from crop production. METHODS: This study used input-output data collected from 10,689 rice farms and 5220 wheat farms across India to estimate technical efficiency, global warming potential, and emission intensity (GHG emissions per unit of crop production) under the existing crop production practices. The GHG emissions from rice and wheat production were estimated using the CCAFS Mitigation Options Tool (CCAFS-MOT) and the technical efficiency of production was estimated through a stochastic production frontier analysis. RESULTS AND CONCLUSIONS: Results suggest that improving technical efficiency in crop production can reduce emission intensity but not necessarily total emissions. Moreover, our analysis does not support smallholders tend to be technically less efficient and the emissions per unit of food produced by smallholders can be relatively high. Alarge proportion of smallholders have high technical efficiency, less total GHG emissions, and low emissions intensity. This study indicates the levels of technical efficiency and GHG emission are largely influenced by farming typology, i.e. choice and use of existing technologies and management practices in crop cultivation. SIGNIFICANCE: This study will help to promote existing improved technologies targeting GHG emissions reduction from the agriculture production systems.

Technical Efficiency Interventions CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA MITIGATION PRODUCTIVITY CROP PRODUCTION GREENHOUSE GAS EMISSIONS

Modelo híbrido de sistemas energéticos para la evaluación del uso de energías renovables

Carlos Iván Torres González (2020, [Tesis de maestría])

En este trabajo proponemos un modelo híbrido para evaluar diferentes escenarios de generación de electricidad con energías renovables que maximiza el bienestar social desde la perspectiva económica contemplando un enfoque técnico sobre la estructura de costos de producción de electricidad. Adicionalmente, realizamos 2 simulaciones del modelo propuesto al sistema eléctrico de Baja California Sur para 10 períodos, contemplando 4 escenarios de producción limpia diferentes. De los resultados observados en ambas simulaciones podemos remarcar 2 puntos en términos de políticas públicas. El primer punto es la importancia de tener múltiples generadores que funcionen con combustibles renovables si se desea producir una proporción significativa de electricidad con FER. El segundo punto es el trade-off entre bienestar y emisiones de CO2. Los resultados sugieren que el aumento del consumo de electricidad es un elemento importante para aumentar el bienestar social. A su vez, el aumento de consumo eléctrico implica un aumento de producción, y por tanto un aumento de emisiones de CO2. Los resultados de la segunda simulación sugieren que con el aumento de la capacidad de generación limpia y costos eficientes, se pueden alcanzar niveles de bienestar casi iguales a los tradicionales, pero con la mitad de emisiones de CO2.

Electric power production -- Effect of renewable energy sources on -- Mexico -- Baja California Sur (State) -- 2015 -- Mathematical models. Carbon dioxide mitigation -- Effect of renewable energy sources on -- Mexico -- Baja California Sur (State) -- 2015 -- Mathematical models. CIENCIAS SOCIALES CIENCIAS SOCIALES

Agua, gobierno y minería: ¿Por qué el medio ambiente no es prioridad en la agenda pública?

ANA MARIA HERRERA CRUZ JUAN ANTONIO BARRON SEVILLA (2022, [Artículo])

Valorar la escasez del agua, la regulación gubernamental y a la minería, es poner en la balanza la famosa relación costo beneficio. No es necesario ser un erudito para saber cuál es la elección de nuestros gobiernos Prevaleciendo en este caso la economía y un aparente desarrollo contra la preservación del medio ambiente. Lo que resulta urgente es un nuevo planteamiento de prioridades para la resolución de problemas que aquejan el acceso al agua como derecho humano.

ESCASEZ DEL AGUA IMPACTO MINERO MEXICO POLITICAS AMBIENTALES INGENIERÍA Y TECNOLOGÍA CIENCIAS TECNOLÓGICAS TECNOLOGÍA MINERA OTRAS OTRAS

Sequía: causas y efectos de un fenómeno global

David Ortega Gaucin (2013, [Artículo])

Este artículo tiene como objetivo proporcionar los elementos teóricos básicos que permitan conocer y comprender las causas y los efectos de la sequía a nivel mundial, así como dimensionar la magnitud de los impactos provocados por este fenómeno en la sociedad global y, específicamente, en México.

Sequías Condiciones sociales México CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA

Evaluación de biofiltros de arena como sistemas de desinfección unifamiliares en comunidades rurales

Maricarmen Espinosa Bouchot SANDRA VAZQUEZ VILLANUEVA (2011, [Documento de trabajo])

Este estudio se enfoca a la evaluación de la biofiltración como alternativa de desinfección de agua en comunidades rurales. Para ello, se construyen biofiltros en dos configuraciones: rectangular y cilíndrica y de dos materiales: concreto y polietileno de alta densidad. Cabe mencionar que el biofiltro rectangular de concreto ya ha sido reportado su empleo por la literatura, no así el de polietileno. El objetivo es buscar las mejores condiciones de operación con el fin posterior de poder ser transferidas a comunidades rurales. En este trabajo se reportan a detalle, como parte de los resultados, las etapas de construcción de los biofiltros de concreto y de polietileno, ya que el diseño del prototipo es una parte importante para el éxito del proceso de filtración. Otra parte esencial del proceso es la puesta en marcha de los prototipos, en donde es necesario conceder al sistema el tiempo necesario para la formación de la capa biológica. Finalmente, se reportan los resultados referentes a las pruebas de laboratorio que se llevaron a cabo para monitorear la eficiencia de remoción de los contaminantes en especial de los microorganismos patógenos.

Filtros biológicos Filtros de arena Evaluación Zonas rurales Informes de proyectos México INGENIERÍA Y TECNOLOGÍA

Viabilidad y barreras para el ejercicio del derecho humano al agua y saneamiento en México

RICARDO VICTOR LOPEZ MERA JOSE LUIS MARTINEZ RUIZ (2014, [Libro])

El libro tiene dos objetivos principales: por un lado, la necesidad de reflexionar respecto a los retos, alcances y limitaciones sociales, económicas, políticas, ambientales y legales para el ejercicio del derecho humano al agua y, por el otro, el saneamiento en los diferentes escenarios del país.

Derecho humano al agua Saneamiento Estudios de factibilidad México CIENCIAS SOCIALES