David Brown
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
David Brown has a total of 52 co-authors. Here are the top co-authors by number of shared publications:
- Jacob van Etten
Digital Inclusion, Bioversity International, Montpellier, France
4 shared publications - Kauê de Sousa
Digital Inclusion, Bioversity International, Montpellier, France
4 shared publications - Hale Ann Tufan
Cornell University, Ithaca, USA
3 shared publications - Lewis Machida
Biodiversity for Food & Agriculture, Bioversity International c/o National Agricultural Research Laboratories (Kawanda) Kampala Uganda
3 shared publications Jacob van Etten
2 shared publications- Jonathan Steinke
Sustainable Land Use in Developing Countries Leibniz Centre for Agricultural Landscape Research (ZALF) Eberswalder Straße 84 15374 Müncheberg Germany
2 shared publications
Latest Publications
- Open Access
- 21 January 2026
- Published by Wiley in Agricultural & Environmental Letters
- Vol. 11 (1)
Toward crop variety recommender systems
Choosing an optimal crop variety to plant is one of the most important decisions faced by farmers. Nowadays, recommender systems are almost ubiquitous in several human activities, except in agriculture, and more deeply absent in crop variety decision‐making. This commentary presents the potential applications of crop variety recommender systems, describing the elements required for their implementation and adoption, and proposing new research areas to address the major research gaps. This work aims to motivate the scientific community at the intersection of agriculture, environmental science, data science, digital technologies, and computer science to work toward the development and application of recommender systems to support crop variety decision‐making.
- 21 January 2026
- Published by Wiley in Agricultural & Environmental Letters
- Vol. 11 (1)
Open AccessToward crop variety recommender systems
Choosing an optimal crop variety to plant is one of the most important decisions faced by farmers. Nowadays, recommender systems are almost ubiquitous in several human activities, except in agriculture, and more deeply absent in crop variety decision‐making. This commentary presents the potential applications of crop variety recommender systems, describing the elements required for their implementation and adoption, and proposing new research areas to address the major research gaps. This work aims to motivate the scientific community at the intersection of agriculture, environmental science, data science, digital technologies, and computer science to work toward the development and application of recommender systems to support crop variety decision‐making.
- Open Access
- 1 November 2025
- Published by Wiley in Crop Science
- Vol. 65 (6)
AI‐based data synthesis of crop trait prioritization studies
Synthesis of data from crop trait prioritization studies (CTPS) can provide insights to support decision‐making, such as institutional funding allocation, and trait prioritization in crop improvement programs. This type of data synthesis is constrained by the lack of standardized crop trait terminology and suitable methods to deal with data heterogeneity. Crop trait ontologies provide terminology standardization, but annotating documents to link terms to ontology terms is time‐consuming and may therefore miss trait terminology emerging from CTPS due to a data annotation bottleneck that constrains data synthesis. Natural language processing (NLP) techniques based on large language models (LLMs) can help in extracting information from unstructured text with no manual text annotation involved. This study applied NLP to synthesize unstructured text data extracted from CTPS by a recently published scoping review. Results show that (1) the trait vocabulary diversity used in CTPS varies per crop and by gender intentionality of CTPS, (2) crop trait preferences increasingly focus on food quality and climate adaptation traits, and (3) existing crop ontologies provide a good coverage of terms found in CTPS but might require the addition of terms, especially in crops such as cassava and sweet potato. This study demonstrates the utility of applying NLP and LLM to synthesize trait preference data across crops and timescales, potentially modeling an approach for broader utility to breeding programs and crop ontology curators alike.
- 1 November 2025
- Published by Wiley in Crop Science
- Vol. 65 (6)
Open AccessAI‐based data synthesis of crop trait prioritization studies
Synthesis of data from crop trait prioritization studies (CTPS) can provide insights to support decision‐making, such as institutional funding allocation, and trait prioritization in crop improvement programs. This type of data synthesis is constrained by the lack of standardized crop trait terminology and suitable methods to deal with data heterogeneity. Crop trait ontologies provide terminology standardization, but annotating documents to link terms to ontology terms is time‐consuming and may therefore miss trait terminology emerging from CTPS due to a data annotation bottleneck that constrains data synthesis. Natural language processing (NLP) techniques based on large language models (LLMs) can help in extracting information from unstructured text with no manual text annotation involved. This study applied NLP to synthesize unstructured text data extracted from CTPS by a recently published scoping review. Results show that (1) the trait vocabulary diversity used in CTPS varies per crop and by gender intentionality of CTPS, (2) crop trait preferences increasingly focus on food quality and climate adaptation traits, and (3) existing crop ontologies provide a good coverage of terms found in CTPS but might require the addition of terms, especially in crops such as cassava and sweet potato. This study demonstrates the utility of applying NLP and LLM to synthesize trait preference data across crops and timescales, potentially modeling an approach for broader utility to breeding programs and crop ontology curators alike.
- Open Access
- 6 August 2025
- Published by Wiley in Plants, People, Planet
- Vol. 8 (1) , 176-184
Applying large language models to extract information from crop trait prioritization studies
Societal Impact Statement: Investigation of farmers', consumers', and other stakeholders' trait preferences is vital for the adoption and impact of improved crop varieties. While qualitative research methods are known to increase the depth and scope of information from respondents, only 5% of previous trait preference studies used qualitative data in their analyses. We show that AI‐based natural language processing, particularly GPTs, is both a time and cost‐effective mechanism for accurately analyzing open‐ended trait preference data. This will contribute to the selection and prioritization of breeding targets to better meet end‐user needs, with implications for food security and health outcomes globally. Summary: Crop trait preference research is critical for the development of improved crop varieties, guiding breeding programs in setting trait priorities and targets that represent farmers' and consumers' needs. However, there is a dearth of methodological harmonization in trait preference studies, leading to high heterogeneity in collected data and analysis frameworks, which constrains comparability between studies. Qualitative research tools using open‐ended questions are among the most common methods used to elucidate crop trait preferences, but only a fraction of these data are used in analysis. The ascendance of AI tools in data analysis provides an opportunity to enhance capitalization of these data from open‐ended question types. We use natural language processing (NLP) techniques, including generative pretrained transformer (GPT) models, to elucidate labels from open‐ended question responses and perform multilabel text classification. We compare these labels to pre‐codes from close‐ended questions, as well as to existing crop trait ontology terms. We find that analyzing responses to open‐ended questions using NLP leads to information gain, including an increase in diversity of traits and insight into their social functions. We conclude that using NLP‐based approaches would allow breeding teams to extract trait terms from open‐ended question responses efficiently and to compare these to both existing ontology terms and close‐ended survey data. Our findings reveal the importance of using open‐ended questions to inform survey codes in mixed methods research design for trait preference studies.
- 6 August 2025
- Published by Wiley in Plants, People, Planet
- Vol. 8 (1) , 176-184
Open AccessApplying large language models to extract information from crop trait prioritization studies
Societal Impact Statement: Investigation of farmers', consumers', and other stakeholders' trait preferences is vital for the adoption and impact of improved crop varieties. While qualitative research methods are known to increase the depth and scope of information from respondents, only 5% of previous trait preference studies used qualitative data in their analyses. We show that AI‐based natural language processing, particularly GPTs, is both a time and cost‐effective mechanism for accurately analyzing open‐ended trait preference data. This will contribute to the selection and prioritization of breeding targets to better meet end‐user needs, with implications for food security and health outcomes globally. Summary: Crop trait preference research is critical for the development of improved crop varieties, guiding breeding programs in setting trait priorities and targets that represent farmers' and consumers' needs. However, there is a dearth of methodological harmonization in trait preference studies, leading to high heterogeneity in collected data and analysis frameworks, which constrains comparability between studies. Qualitative research tools using open‐ended questions are among the most common methods used to elucidate crop trait preferences, but only a fraction of these data are used in analysis. The ascendance of AI tools in data analysis provides an opportunity to enhance capitalization of these data from open‐ended question types. We use natural language processing (NLP) techniques, including generative pretrained transformer (GPT) models, to elucidate labels from open‐ended question responses and perform multilabel text classification. We compare these labels to pre‐codes from close‐ended questions, as well as to existing crop trait ontology terms. We find that analyzing responses to open‐ended questions using NLP leads to information gain, including an increase in diversity of traits and insight into their social functions. We conclude that using NLP‐based approaches would allow breeding teams to extract trait terms from open‐ended question responses efficiently and to compare these to both existing ontology terms and close‐ended survey data. Our findings reveal the importance of using open‐ended questions to inform survey codes in mixed methods research design for trait preference studies.
- Open Access
- 3 July 2024
- Published by Wiley in Crop Science
- Vol. 64 (5) , 2679-2697
On‐farm evaluation of cassava clones using the triadic comparison of technology options approach
The triadic comparison of technology options (tricot) approach to participatory varietal selection has been demonstrated to scale out the on‐farm testing of elite candidate crop varieties. In this study, we evaluated elite clones of cassava (Manihot esculenta Crantz) using the tricot approach. We sought to (1) synthesize on‐farm trial data from two cycles evaluating different sets of elite cassava clones; (2) assess the agronomic performance of elite cassava clones considering sociodemographic and climatic factors; and (3) assess the performance of elite cassava clones for both agronomic and food quality traits. The study involved 10 districts in Uganda, two cycles/seasons of evaluation, 20 elite cassava clones, one check variety, and 294 men and 320 women farmers. Our results indicate that the agronomic performance of elite cassava clones was influenced more by geographic than sociodemographic factors. Our analysis identified the number of days with rainfall higher than 20 mm as the most influencing climatic factor over agronomic performance. Further, the study identified superior elite cassava clones UG110164, UGC14170, and UG120193 as promising candidate varieties for release, targeting food products. Overall, our study emphasizes the important contribution of end‐users to crop improvement and provides insights into use of tricot on‐farm testing methodology to evaluate elite cassava clones during cassava variety development in Uganda, which can be used to support decision making for variety release.
- 3 July 2024
- Published by Wiley in Crop Science
- Vol. 64 (5) , 2679-2697
Open AccessOn‐farm evaluation of cassava clones using the triadic comparison of technology options approach
The triadic comparison of technology options (tricot) approach to participatory varietal selection has been demonstrated to scale out the on‐farm testing of elite candidate crop varieties. In this study, we evaluated elite clones of cassava (Manihot esculenta Crantz) using the tricot approach. We sought to (1) synthesize on‐farm trial data from two cycles evaluating different sets of elite cassava clones; (2) assess the agronomic performance of elite cassava clones considering sociodemographic and climatic factors; and (3) assess the performance of elite cassava clones for both agronomic and food quality traits. The study involved 10 districts in Uganda, two cycles/seasons of evaluation, 20 elite cassava clones, one check variety, and 294 men and 320 women farmers. Our results indicate that the agronomic performance of elite cassava clones was influenced more by geographic than sociodemographic factors. Our analysis identified the number of days with rainfall higher than 20 mm as the most influencing climatic factor over agronomic performance. Further, the study identified superior elite cassava clones UG110164, UGC14170, and UG120193 as promising candidate varieties for release, targeting food products. Overall, our study emphasizes the important contribution of end‐users to crop improvement and provides insights into use of tricot on‐farm testing methodology to evaluate elite cassava clones during cassava variety development in Uganda, which can be used to support decision making for variety release.
- Open Access
- 9 October 2023
- Published by Wiley in Agronomy Journal
- Vol. 115 (6) , 2990-3009
Rank‐based data synthesis of heterogeneous trials to identify the effects of climatic factors on the reaction of Musa genotypes to black leaf streak disease
Synthesis of crop trial data can generate insights that are not available from the analysis of individual studies, but such synthesis is often constrained by the heterogeneity of data among studies. Rank‐based data synthesis provides the flexibility to combine data of heterogeneous types and from different sources. We demonstrate the application of rank‐based data synthesis of heterogeneous trial data to assess the effect of climatic factors on the reaction of several Musa genotypes to black leaf streak disease (BLSD; caused by Pseudocercospora fijiensis [sexual morph: Mycosphaerella fijiensis]). We aggregated data from the main public repositories of Musa trial data. We applied model‐based recursive partitioning with the Plackett–Luce model, using climatic data as covariates. The model identified the maximum length of the dry spell as the main variable influencing differences in genotypic response to BLSD, dividing the aggregated trial dataset into humid and dry environments. We found differences in the reaction of genotypes to BLSD between these environments. In humid environments, NARITA 8 was found to be the most resistant genotype, while in dry environments FHIA‐01 was the best performing improved genotype. We also assessed reliability, which is the probability of outperforming the reference genotype (Calcutta 4). In humid environments, NARITA 2, NARITA 8, and FHIA‐01 had the highest reliability, while in dry environments only the landrace Saba surpassed 50% reliability. The information generated by our data synthesis approach supports selecting Musa genotypes for further evaluations at new locations.
- 9 October 2023
- Published by Wiley in Agronomy Journal
- Vol. 115 (6) , 2990-3009
Open AccessRank‐based data synthesis of heterogeneous trials to identify the effects of climatic factors on the reaction of Musa genotypes to black leaf streak disease
Synthesis of crop trial data can generate insights that are not available from the analysis of individual studies, but such synthesis is often constrained by the heterogeneity of data among studies. Rank‐based data synthesis provides the flexibility to combine data of heterogeneous types and from different sources. We demonstrate the application of rank‐based data synthesis of heterogeneous trial data to assess the effect of climatic factors on the reaction of several Musa genotypes to black leaf streak disease (BLSD; caused by Pseudocercospora fijiensis [sexual morph: Mycosphaerella fijiensis]). We aggregated data from the main public repositories of Musa trial data. We applied model‐based recursive partitioning with the Plackett–Luce model, using climatic data as covariates. The model identified the maximum length of the dry spell as the main variable influencing differences in genotypic response to BLSD, dividing the aggregated trial dataset into humid and dry environments. We found differences in the reaction of genotypes to BLSD between these environments. In humid environments, NARITA 8 was found to be the most resistant genotype, while in dry environments FHIA‐01 was the best performing improved genotype. We also assessed reliability, which is the probability of outperforming the reference genotype (Calcutta 4). In humid environments, NARITA 2, NARITA 8, and FHIA‐01 had the highest reliability, while in dry environments only the landrace Saba surpassed 50% reliability. The information generated by our data synthesis approach supports selecting Musa genotypes for further evaluations at new locations.
- Open Access
ag5Tools: An R package for downloading and extracting agrometeorological data from the AgERA5 database
- Open Access
- 24 October 2022
- Published by Wiley in Crop Science
- Vol. 62 (6) , 2246-2266
Rank‐based data synthesis of common bean on‐farm trials across four Central American countries
Location‐specific information is required to support decision making in crop variety management, especially under increasingly challenging climate conditions. Data synthesis can aggregate data from individual trials to produce information that supports decision making in plant breeding programs, extension services, and of farmers. Data from on‐farm trials using the novel approach of triadic comparison of technologies (tricot) are increasingly available, from which more insights could be gained using a data synthesis approach. The objective of our study was to present the applicability of a rank‐based data synthesis approach to several datasets from tricot trials to generate location‐specific information supporting decision making in crop variety management. Our study focuses on tricot data from 14 trials of common bean (Phaseolus vulgarisL.) performed between 2015 and 2018 across four countries in Central America (Costa Rica, El Salvador, Honduras, and Nicaragua). The combined data of 17 common bean genotypes were rank aggregated and analyzed with the Plackett–Luce model. Model‐based recursive partitioning was used to assess the influence of spatially explicit environmental covariates on the performance of common bean genotypes. Location‐specific performance was predicted for the three main growing seasons in Central America. We demonstrate how the rank‐based data synthesis methodology allows integrating tricot trial data from heterogenous sources to provide location‐specific information to support decision making in crop variety management. Maps of genotype performance can support decision making in crop variety evaluation such as variety recommendations to farmers and variety release processes.
- 24 October 2022
- Published by Wiley in Crop Science
- Vol. 62 (6) , 2246-2266
Open AccessRank‐based data synthesis of common bean on‐farm trials across four Central American countries
Location‐specific information is required to support decision making in crop variety management, especially under increasingly challenging climate conditions. Data synthesis can aggregate data from individual trials to produce information that supports decision making in plant breeding programs, extension services, and of farmers. Data from on‐farm trials using the novel approach of triadic comparison of technologies (tricot) are increasingly available, from which more insights could be gained using a data synthesis approach. The objective of our study was to present the applicability of a rank‐based data synthesis approach to several datasets from tricot trials to generate location‐specific information supporting decision making in crop variety management. Our study focuses on tricot data from 14 trials of common bean (Phaseolus vulgarisL.) performed between 2015 and 2018 across four countries in Central America (Costa Rica, El Salvador, Honduras, and Nicaragua). The combined data of 17 common bean genotypes were rank aggregated and analyzed with the Plackett–Luce model. Model‐based recursive partitioning was used to assess the influence of spatially explicit environmental covariates on the performance of common bean genotypes. Location‐specific performance was predicted for the three main growing seasons in Central America. We demonstrate how the rank‐based data synthesis methodology allows integrating tricot trial data from heterogenous sources to provide location‐specific information to support decision making in crop variety management. Maps of genotype performance can support decision making in crop variety evaluation such as variety recommendations to farmers and variety release processes.
- 24 March 2022
- Published by The R Foundation
ag5Tools: Toolbox for Downloading and Extracting Copernicus AgERA5 Data
- 24 March 2022
- Published by The R Foundation
ag5Tools: Toolbox for Downloading and Extracting Copernicus AgERA5 Data
- 8 March 2022
- Published by The R Foundation
gosset: Tools for Data Analysis in Experimental Agriculture
- 8 March 2022
- Published by The R Foundation
gosset: Tools for Data Analysis in Experimental Agriculture