About

Louis Longchamps is an Assistant Professor of Digital Agronomy in the Soil & Crop Sciences Section at the School of Integrative Plant Science since 2020. His research focuses on simplifying and enhancing the Farmer-Centric On-Farm Experimentation (OFE) process by developing tools that improve data collection, organization, and analysis, thereby empowering New York farms to become more sustainable and resilient. His work involves creating digital solutions that facilitate research collaboration between farmers and scientists, advancing precision agriculture through soil and crop sensing, and improving input use efficiency in field crops. Previously, Longchamps worked for Agriculture and Agri-Food Canada, where he concentrated on optimizing nitrogen management using remote sensing and reducing nitrous oxide emissions through variable-rate application. He was also a co-leader of a Living Laboratory aimed at co-creating solutions with farmers to reduce the environmental impacts of agriculture on the St. Lawrence River’s ecosystems. He earned his PhD at Laval University, with a thesis on the spatial structure of weed populations in corn fields and site-specific weed management, followed by postdoctoral work at Colorado State University studying variable rate irrigation and nitrogen management. His outreach efforts focus on integrating research and practice in digital agronomy through collaboration with farmers, leveraging digital tools such as data contextualization, multi-farm data pooling, and artificial intelligence to enhance decision-making, profitability, and environmental stewardship.

Research topics

• Agronomy
• Environmental science
• Engineering
• Agricultural engineering
• Mathematics
• Geography
• Business
• Biology

Selected publications

• Yield forecasting in maize: Performance and limits of unmanned aerial vehicle and PlanetScope remote sensing across multiple growth cycles

  Computers and Electronics in Agriculture · 2026-01-19

  article
  PublisherDOI

• Integrating stability zones and machine learning for enhanced crop management

  Precision Agriculture · 2026-03-09

  articleOpen access

  Abstract Purpose Sustainable agriculture requires both high and stable crop yields. Whilegenotype-environment-management (G×E×M) interactions influence yield stability, implementingsuch understanding into practical applications demands better analytical tools. Yield StabilityZones (YSZ) effectively identify stable and unstable production areas, yet their implementationhas been constrained by data limitations and interpretability challenges. Precision agriculturenow enables the application of YSZ approaches through multi-year yield and management data,while interpretable machine learning (ML) can decode yield drivers into actionable insights. Thisstudy develops a universal framework integrating YSZ and interpretable ML to enhancedecision-making in variable agricultural environments, using citrus production as a case study. Methods Analysis of five-year yield, soil, and rainfall data (2012–2016) from a 250-ha field todevelop an YSZ framework, assess temporal yield stability and interactions by ‘comparing single-year versus multi-year data’ on a real production scenario, and integrate machine learning(decision trees) to promote interpretation of yield factors and support optimized cropmanagement. Results Significant temporal dynamics in soil-yield interactions was found. Single-year assessments fail to capture critical interannual variability in yield drivers. YSZ effectivelydelineated spatially consistent production areas, distinguishing stable high-yielding zones fromunstable regions, while decision trees identified key drivers of yield variability. Conclusion Together, these tools provide a data-driven approach to optimize crop production sustainably.Our methodology bridges a critical gap in crop analytics and offers scalable insights forprecision agriculture under dynamic production systems.

  PublisherOA PDFDOI

• Farmer-centric on-farm experimentation as everyday transformative change for climate adaptation: a systematic review

  Ecology and Society · 2026-01-01

  articleOpen accessSenior author

  A growing proportion of the agricultural research community has been calling for a systemic restructuring of farmer-researcher relationships to accelerate learning and facilitate transformations toward a climate-resilient food system. One set of approaches, farmer-centric on-farm experimentation (OFE), is gaining ground as a renewed means for scientists and other agri-food system actors to co-create knowledge with farmers about their own farms through their everyday adaptation practices. Despite increasing interest, there has been little systematic assessment of how farmer-centric OFE principles and processes transform farmers’ everyday adaptive capabilities to better adapt to climate change. This study fills this gap by drawing from second-order action-oriented transformation research essentials, which aim to facilitate transformative change by shifting how knowledge is produced in scientific research. We examined 39 peer-reviewed articles by considering how farmer-centric OFE supports transformative change in relation to climate change adaptation through these research essentials. Our results confirm substantial variation between OFEs in their definitions of transformative change, methods used, and participation levels of different actors. We identify two major approaches to OFE, one grounded in reflexivity, which explicitly recognizes transformation, and another based on adoption-based reasoning. We highlight the importance of co-learning as a meaningful shift from scientist-led research by repositioning the role of scientists to purposively work with farmers for transformative change. We then suggest pathways for researchers utilizing farmer-centric OFE to incorporate action-oriented transformation research essentials into their approaches, most notably by better integrating social sciences and processes into agricultural innovations.

  PublisherOA PDFDOI

• A Geospatial Data Retrieval Tool (GeoDaRT) for Contextualizing On-Farm Experimentation in the United States of America

  SSRN Electronic Journal · 2026-01-01

  preprintOpen accessSenior author
  PublisherDOI

• Strengthening farmer-led experiments through agronomic and causal inference frameworks

  2025-06-27

  preprintOpen access1st authorCorresponding

  This study explores how scientists can support on-farm experiments using analytical methods that align with farmers’ endogenous learning processes. Four maize farmers across 10 site-years in New York participated in this study to evaluate the effectiveness of a nitrogen-fixing inoculant (NFI) applied with a reduced side-dress nitrogen rate. Farmers designed and implemented their own experiments using a range of layouts, including side-by-side comparisons and strip trials. Two analytical approaches were compared: a quantitative yield analysis using spatial regression, and a causal pathway analysis based on mechanistic steps informed by field sampling (e.g., qPCR detection of NFI organisms, nitrogen nutrition index, and yield). While yield data suggested positive or neutral treatment effects at all sites when simply comparing yield average, the spatial regression analysis and causal pathway analysis identified positive outcomes in only 7 or 4 of 10 site-years respectively, reflecting a more conservative interpretation of efficacy. Both methods provided consistent conclusions at 4 out of 10 site-years, demonstrating the contribution of metrics other than yield in the interpretation process. Findings suggest that simple causal diagrams can structure data collection and interpretation in ways aligned with farmers’ goals. Supporting farmer experiments with digital agronomy, mechanistic reasoning, and site-specific data enhances learning outcomes and scientific rigor without requiring formal replication. This work contributes to the development of collaborative, scalable methodologies that integrate farmer knowledge and scientific analysis in OFE.

  PublisherOA PDFDOI

• Using causal diagrams to interpret unreplicated on-farm experiments

  2025-06-18

  book-chapterOpen access1st authorCorresponding

  Farmer-led on-farm experimentation (OFE) provides valuable insights but often lacks rigorous interpretation, especially for unreplicated experiments. This study applied causal diagrams to enhance understanding of N-fixing bacteria (NFB) treatments in maize. Data on NFB survival, plant N status, and yield informed a stepwise “interpretation key,” allowing site-specific conclusions. Results showed more nuanced analysis causal diagrams backed by data compared to farmers’ yieldbased conclusions, emphasizing the value of additional data. While subjective elements remain in diagram design, this approach improves decision-making and fosters collaboration between farmers and researchers. Refining this method could enhance OFE scalability and farmer-driven innovation.

  PublisherOA PDFDOI

• 61. The Cornell Agricultural Systems Testbed and Demonstration site (CAST) for the farm of the future

  Animal - science proceedings · 2025-10-01

  article
  PublisherDOI

• Farmer-centric On-Farm Experimentation: digital tools for a scalable transformative pathway

  Agronomy for Sustainable Development · 2025-03-17 · 4 citations

  articleOpen access

  Abstract This virtual issue reports on the use of digital technologies in On-Farm Experimentation (OFE) in varied farming systems across the world. The authors investigated diverse questions across contrasted environments and scientific domains, with methodologies that included review, empirical studies, interviews, and reflexive accounts. The contributions thus showcase the multiplicity of research directions that are relevant to OFE. This includes addressing the two intertwined types of research objects in OFE: the farmers’ questions (how to improve management) and the methodologies required to address these (how to improve research through OFE)—with the notable support of digital tools. The issue includes a systematic review exploring OFE practices and farmer-researcher relationships as reported in the scientific literature; a meta-analysis comparing experimental scales in the USA; reflexive analyzes on a feed assessment tool and a tree crop decision support system rooted in OFE that are connecting farmers and researchers in Africa; a retrospective on a large CGIAR program combining citizen sciences and OFE; the use of video recordings and work analysis to characterize farmers’ knowledge in French vineyards; and in the same sector in Australia, two accounts of the use of digital tools in spatially explicit OFE: one an investigation into farmers’ and consultants’ perceptions, the other a retrospective on the roles of precision agriculture. Findings from these examples validate the use of varied digital tools to scale the design, implementation, and learning stages of OFE processes. These include how to better harness and bridge the knowledge of farmers, researchers and other parties, examples of data management and analytics, the improved interpretation of results, and capitalizing on experiences. The international conference this issue was part of also led to acknowledgement of a lack of policy linkages, required to scale OFE endeavors by incentivizing institutional change toward more farmer-centric research practices and responsible digital deployment.

  PublisherOA PDFDOI

• AI-enhanced potato yield assessment using Sentinel-2 imaging

  2025-06-18

  book-chapterOpen access

  This paper presents a hybrid approach using AI and satellite remote sensing to forecast pre-harvest potato yields. Experiments on four fields in Prince Edward Island, Canada, involved multispectral images from Sentinel-2 and ground truth data from 3 m harvest tests. Three machine learning models were tested, with the random forest model showing the best results (RRMSE=13.8%, RMAE=11.3%). The study confirmed the potential of AI and multispectral data in improving yield estimation accuracy, marking a significant step forward for digital agriculture. Future work should integrate more data sources and advanced AI methods.

  PublisherOA PDFDOI

• Soil moisture sensor location-allocation using spatial association of surface moisture data

  Smart Agricultural Technology · 2025-04-04 · 5 citations

  articleOpen access

  Balancing cost and performance is typically required when deploying a soil moisture sensor array. The sensor array's performance is essentially dependent on the appropriate placement of the sensors, which is fundamentally a location-allocation problem. In this study, a novel approach based on spatial association of surface soil moisture (SASM) is presented. It proposes selecting a sub-sample of sensor locations that best represent the spatial distribution of soil moisture while maximizing the variance in soil moisture with the minimum number of sample sites. This approach was tested at two sites with maize cultivated fields in Colorado. Neutron probe readings were collected at 15 cm depth across 41 and 31 locations throughout the entire crop growing season in two maize fields in Colorado. The number of soil sensors were optimized in a range of 17–19 with optimum site configuration for all different data acquisition dates. A global measure of spatial association (GMSA) analysis indicated consistency in spatial pattern between reduced number of sub-samples and original samples. Strategic sensor placement, driven by insights into soil-water dynamics patterns and intrinsic field properties, is essential for informed decision-making in water management within an irrigated maize field.

  PublisherDOI

Frequent coauthors

• Raj Khosla

  35 shared

• B. Panneton

  Agriculture and Agri-Food Canada

  14 shared

• Gilles Leroux

  Institut National de Recherches Archéologiques Préventives

  7 shared

• Jeff Siegfried

  Colorado State University

  6 shared

• Dario Sacco

  6 shared

• Jean‐Michel Roger

  Université de Montpellier

  6 shared

• Serge Guillaume

  ITAP - Technologies et Méthodes pour les Agricultures de demain

  6 shared

• Eleonora Cordero

  6 shared