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

The generation challenge programme platform: Semantic standards and workbench for crop science

Richard Bruskiewich Guy Davenport Mathieu Rouard Reinhard Simon Samart Wanchana Trushar Shah Victor Jun Ulat Andrew Farmer Pankaj Jaiswal Mark Wilkinson David Marshall Alyssa Collins (2008, [Artículo])

CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA CROP IMPROVEMENT GENETIC RESOURCES PLANT BREEDING BIODIVERSITY COMPUTER APPLICATIONS DIGITAL TECHNOLOGY DATA PROCESSING

Review of Nationally Determined Contributions (NCD) of Vietnam from the perspective of food systems

Tek Sapkota (2023, [Documento de trabajo])

Over the past decades, Vietnam has significantly progressed and has transformed from being a food-insecure nation to one of the world’s leading exporters in food commodities, and from one of the world’s poorest countries to a low-middle-income country. The agriculture sector is dominated by rice and plays a vital role in food security, employment, and foreign exchange. Vietnam submitted its updated Nationally Determined Contributions (NDC) in 2022 based on the NDC 2020. There is a significant increase in greenhouse gas (GHG) emission reduction, towards the long-term goals identified in Vietnam’s National Climate Change Strategy to 2025, and efforts are being made to fulfil the commitments made at COP26. The Agriculture Sector is the second-largest contributor of GHG emissions in Vietnam, accounting for 89.75 MtCO2eq, which was about 31.6 percent of total emissions in 2014. Rice cultivation is the biggest source of emissions in the agriculture sector, accounting for 49.35% of emissions from agriculture. The total GHG removal from Land Use, Land Use Change and Forestry (LULUCF) in 2014 was -37.54 MtCO2eq, of which the largest part was from the forest land sub-sector (35.61 MtCO2eq), followed by removal from croplands (7.31 MtCO2eq) (MONRE 2019).

CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA CLIMATE CHANGE GREENHOUSE GAS EMISSIONS FOOD SYSTEMS LAND USE CHANGE AGRICULTURE POLICIES DATA ANALYSIS

Review of Nationally Determined Contributions (NCD) of Colombia from the perspective of food systems

Tek Sapkota (2023, [Documento de trabajo])

Food is a vital component of Colombia's economy. The impact of climate change on agriculture and food security in the country is severe. The effects have resulted in decreased production and in the productivity of agricultural soil. Desertification processes are accelerating and intensifying. Colombia's government formally submitted its Nationally Determined Contribution (NDC) on December 29, 2020. This paper examines Colombia's NDC from the standpoint of the food system.

CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA CLIMATE CHANGE GREENHOUSE GAS EMISSIONS FOOD SYSTEMS LAND USE CHANGE AGRICULTURE POLICIES DATA ANALYSIS FOOD WASTES

Partial least squares enhance multi-trait genomic prediction of potato cultivars in new environments

Rodomiro Ortiz Paulino Pérez-Rodríguez Osval Antonio Montesinos-Lopez Jose Crossa (2023, [Artículo])

Potato Traits Cross-Validation Breeding Data CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA LEAST SQUARES METHOD POTATOES ENVIRONMENT PLANT BREEDING

Estimation of general and specific combining ability effects for quality protein maize inbred lines

Adefris Teklewold Dagne Wegary Gissa (2022, [Artículo])

General Combining Ability Specific Combining Ability CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA COMBINING ABILITY MAIZE PROTEIN QUALITY INBRED LINES DATA ANALYSIS

Monitoreo e Instalación visual de señales a un motor eléctrico de inducción de instalación trifásica de forma jaula de ardilla, mediante la implementación de tecnología industria 4.0

Luis Ricardo Uribe Dávila (2023, [Tesis de maestría])

Vivimos la industria 4.0, misma que no es nueva, ya que sus orígenes se remontan a finales de la década de los 2000, en Alemania. Un pilar de la industria 4.0 es el análisis de datos, conocido como Big Data. El conocer los datos de un proceso, de un estudio, ayuda en gran medida a predecir el comportamiento que tendrá el proceso o la máquina a estudiar en un periodo a corto o mediano plazo. En el presente proyecto se analizan los datos arrojados por un motor eléctrico de corriente alterna, del tipo inducción, jaula de ardilla. El motor está diseñado para trabajar de manera continua, sin embargo, el uso que se le da, es meramente educativo; es decir, no sobre pasa las 15 horas por semana de uso. Mediante la toma de datos de las tres fases de corriente RMS o corriente de valor eficaz que posee el motor eléctrico que se realizará con el microcontrolador Arduino UNO, se analizarán los mismos mediante el software de cómputo numérico MATLAB, ordenando los datos, descartando valores que no aporten información relevante para lograr la predicción de datos. Por último, se llevará a conocer este proyecto a la carrera mecatrónica, área sistemas de manufactura flexible y área automatización, con el fin de que puedan observar de una mejor manera la aplicación y funcionamiento de uno de los pilares de la actual industria 4.0.

We live in industry 4.0, which is not new, since its origins date back to the late 2000s, in Germany. One pillar of industry 4.0 is data analysis, known as Big Data. Knowing the data of a process, of a study, helps greatly to predict the behavior that the process or machine will have to study in a short- or medium-term period. This project analyzes the data released by an electric motor of alternating current, of the type induction, squirrel cage. The engine is designed to work continuously, however, the use given to it is merely educational, that is; only not over spends 15 hours per week of use. By taking data from the three phases of RMS current or effective value current of the electric motor that will be made with the Arduino UNO micro controller, they will be analyzed using MATLAB numerical computing software, ordering the data, discarding values that do not provide relevant information to achieve data prediction. Finally, this project will be presented to the mechatronics career, flexible manufacturing systems area and automation area, so that they can observe in a better way the application and operation of one of the pillars of the current industry 4.0.

Mantenimiento predictivo Regresión lineal Industria 4.0 Big data Corriente RMS Predictive maintenance Linear regression Industry 4.0 Big data RMS Current INGENIERÍA Y TECNOLOGÍA CIENCIAS TECNOLÓGICAS OTRAS ESPECIALIDADES TECNOLÓGICAS OTRAS OTRAS

Visualising the pattern of long-term genotype performance by leveraging a genomic prediction model

Vivi Arief Ian Delacy Thomas Payne Kaye Basford (2022, [Artículo])

Factor Analytic Genotype-By-Year Historical Data Relationship Matrix CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA GENOTYPES PLANT BREEDING SPRING WHEAT RESEARCH

The HUB Model: An evolving concept for knowlegde management among and between stakeholders towards integrated agri-food systems

Jelle Van Loon (2022, [Objeto de congreso])

CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA INNOVATION SYSTEMS FOOD SYSTEMS AGRIFOOD SYSTEMS DATA PROCESSING

Review of Nationally Determined Contributions (NCD) of China from the perspective of food systems

Tek Sapkota (2023, [Documento de trabajo])

China is the largest emitter of greenhouse gases (GHG) and one of the countries most affected by climate change. China's food systems are a major contributor to climate change: in 2018, China's food systems emitted 1.09 billion tons of carbondioxide equivalent (CO2eq) GHGs, accounting for 8.2% of total national GHG emissions and 2% of global emissions. According to the Third National Communication (TNC) Report, in 2010, GHG emissions from energy, industrial processes, agriculture, and waste accounted for 78.6%, 12.3%, 7.9%, and 1.2% of total emissions, respectively, (excluding emissions from land use, land-use change and forestry (LULUCF). Total GHG emissions from the waste sector in 2010 were 132 Mt CO2 eq, with municipal solid waste landfills accounting for 56 Mt. The average temperature in China has risen by 1.1°C over the last century (1908–2007), while nationally averaged precipitation amounts have increased significantly over the last 50 years. The sea level and sea surface temperature have risen by 90 mm and 0.9°C respectively in the last 30 years. A regional climate model predicted an annual mean temperature increase of 1.3–2.1°C by 2020 (2.3–3.3°C by 2050), while another model predicted a 1–1.6°C temperature increase and a 3.3–3.7 percent increase in precipitation between 2011 and 2020, depending on the emissions scenario. By 2030, sea level rise along coastal areas could be 0.01–0.16 meters, increasing the likelihood of flooding and intensified storm surges and causing the degradation of wetlands, mangroves, and coral reefs. Addressing climate change is a common human cause, and China places a high value on combating climate change. Climate change has been incorporated into national economic and social development plans, with equal emphasis on mitigation and adaptation to climate change, including an updated Nationally Determined Contribution (NDC) in 2021. The following overarching targets are included in China's updated NDC: • Peaking carbon dioxide emissions “before 2030” and achieving carbon neutrality before 2060. • Lowering carbon intensity by “over 65%” by 2030 from the 2005 level. • Increasing forest stock volume by around 6 billion cubic meters in 2030 from the 2005 level. The targets have come from several commitments made at various events, while China has explained very well the process adopted to produce its third national communication report. An examination of China's NDC reveals that it has failed to establish quantifiable and measurable targets in the agricultural sectors. According to the analysis of the breakdown of food systems and their inclusion in the NDC, the majority of food system activities are poorly mentioned. China's interventions or ambitions in this sector have received very little attention. The adaptation component is mentioned in the NDC, but is not found to be sector-specific or comprehensive. A few studies have rated the Chinese NDC as insufficient, one of the reasons being its failure to list the breakdown of each sector's clear pathway to achieving its goals. China's NDC lacks quantified data on food system sub-sectors. Climate Action Trackers' "Insufficient" rating indicates that China's domestic target for 2030 requires significant improvements to be consistent with the Paris Agreement's target of 1.5°C temperature limit. Some efforts are being made: for example, scientists from the Institute of Environment and Sustainable Development in Agriculture, Chinese Academy of Agricultural Sciences (IEDA-CAAS) have developed methods for calculating GHG emissions from livestock and poultry farmers that have been published as an industrial standard by the Ministry of Agriculture and Rural Affairs, PRC (Prof Hongmin Dong, personal communication) but this still needs to be consolidated and linked to China’s NDC. The updated Nationally Determined Contributions fall short of quantifiable targets in agriculture and food systems as a whole, necessitating clear pathways. China's NDC is found to be heavily focused on a few sectors, including energy, transportation, and urban-rural development. The agricultural sectors' and food systems' targets are vague, and China's agrifood system has a large carbon footprint. As a result, China should focus on managing the food system (production, processing, transportation, and food waste management) to reduce carbon emissions. Furthermore, China should take additional measures to make its climate actions more comprehensive, quantifiable, and measurable, such as setting ambitious and clear targets for the agriculture sector, including activity-specific GHG-reduction pathways; prioritizing food waste and loss reduction and management; promoting sustainable livestock production and low carbon diets; reducing chemical pollution; minimizing the use of fossil fuel in the agri-system and focusing on developing green jobs, technological advancement and promoting climate-smart agriculture; promoting indigenous practices and locally led adaptation; restoring degraded agricultural soils and enhancing cooperation and private partnership. China should also prepare detailed NDC implementation plans including actions and the GHG reduction from conditional targets.

CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA GREENHOUSE GAS EMISSIONS CLIMATE CHANGE FOOD SYSTEMS LAND USE CHANGE AGRICULTURE POLICIES DATA ANALYSIS FOOD WASTES