Brent Sams
Research Subjects
Brent Sams has a total of 78 co-authors. Here are the top co-authors by number of shared publications:
L. Sanchez
Winegrowing Research GALLO Modesto CA USA
6 shared publicationsLuis Sanchez
Department of Winegrowing Research, E&J Gallo Winery, Modesto, CA, USA
5 shared publicationsNick Dokoozlian
Department of Winegrowing Research, E&J Gallo Winery, Modesto, CA, USA
4 shared publicationsN. Dokoozlian
3 shared publications- Robert G. V. Bramley
CSIRO, Waite Campus Glen Osmond SA 5064 Australia
3 shared publications - Christopher M. Ford
School of Agriculture, Food and Wine, University of Adelaide, Adelaide 5064, South Australia, Australia
2 shared publications
Latest Publications
- Open Access
- 3 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 8932-8945
CMAViT: Integrating Climate, Management, and Remote Sensing Data for Crop Yield Prediction With Multimodel Vision Transformers
Crop yield prediction is essential for agricultural planning but remains challenging due to the complex interactions between weather, climate, and management practices. To address these challenges, we introduce a deep learning-based multimodel called climate-management aware Vision Transformer (CMAViT), designed for pixel-level vineyard yield predictions. CMAViT integrates both spatial and temporal data by leveraging remote sensing imagery and short-term meteorological data, capturing the effects of growing season variations. Additionally, it incorporates management practices, which are represented in text form, using a cross-attention encoder to model their interaction with time-series data. This innovative multimodal transformer tested on a large dataset from 2016 to 2019 covering 2200 hectares and eight grape cultivars including more than 5 million vines, outperforms traditional models like UNet-ConvLSTM, excelling in spatial variability capture and yield prediction, particularly for extreme values in vineyards. CMAViT achieved an R$^{2}$ of 0.84 and an MAPE of 8.22% on an unseen test dataset. Masking specific modalities lowered performance: excluding management practices, climate data, and both reduced R$^{2}$ to 0.73, 0.70, and 0.72, respectively, and raised MAPE to 11.92%, 12.66%, and 12.39%, highlighting each modality’s importance for accurate yield prediction.
- 3 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 8932-8945
Open AccessCMAViT: Integrating Climate, Management, and Remote Sensing Data for Crop Yield Prediction With Multimodel Vision Transformers
Crop yield prediction is essential for agricultural planning but remains challenging due to the complex interactions between weather, climate, and management practices. To address these challenges, we introduce a deep learning-based multimodel called climate-management aware Vision Transformer (CMAViT), designed for pixel-level vineyard yield predictions. CMAViT integrates both spatial and temporal data by leveraging remote sensing imagery and short-term meteorological data, capturing the effects of growing season variations. Additionally, it incorporates management practices, which are represented in text form, using a cross-attention encoder to model their interaction with time-series data. This innovative multimodal transformer tested on a large dataset from 2016 to 2019 covering 2200 hectares and eight grape cultivars including more than 5 million vines, outperforms traditional models like UNet-ConvLSTM, excelling in spatial variability capture and yield prediction, particularly for extreme values in vineyards. CMAViT achieved an R$^{2}$ of 0.84 and an MAPE of 8.22% on an unseen test dataset. Masking specific modalities lowered performance: excluding management practices, climate data, and both reduced R$^{2}$ to 0.73, 0.70, and 0.72, respectively, and raised MAPE to 11.92%, 12.66%, and 12.39%, highlighting each modality’s importance for accurate yield prediction.
- Open Access
- 18 June 2025
- Published by Walter de Gruyter GmbH
- p. 178-183
Comparing the spatial variability of grapevine evapotranspiration from OpenET and fruit composition of Cabernet Sauvignon in California vineyards
OpenET uses publicly available data and employs multiple satellite-driven models to map evapotranspiration (ET) at the field scale. In this study, maps of yield and fruit composition were compared with maps of ET estimates from OpenET in the 2017, 2018, and 2019 seasons to understand how seasonal water use affected vineyard productivity and fruit composition at harvest. Results showed correlations between yield, several parameters of fruit composition, and ET estimates varied by vineyard and season. The results provide insight into the spatial variability of vine water use and its impact on vine performance and support the development of sustainable water use models for optimizing vineyard yield and fruit composition.
- 18 June 2025
- Published by Walter de Gruyter GmbH
- p. 178-183
Open AccessComparing the spatial variability of grapevine evapotranspiration from OpenET and fruit composition of Cabernet Sauvignon in California vineyards
OpenET uses publicly available data and employs multiple satellite-driven models to map evapotranspiration (ET) at the field scale. In this study, maps of yield and fruit composition were compared with maps of ET estimates from OpenET in the 2017, 2018, and 2019 seasons to understand how seasonal water use affected vineyard productivity and fruit composition at harvest. Results showed correlations between yield, several parameters of fruit composition, and ET estimates varied by vineyard and season. The results provide insight into the spatial variability of vine water use and its impact on vine performance and support the development of sustainable water use models for optimizing vineyard yield and fruit composition.
- Open Access
- 25 April 2025
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 139
Predicting crop yield lows through the highs via binned deep imbalanced regression: A case study on vineyards
- 25 April 2025
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 139
Open AccessPredicting crop yield lows through the highs via binned deep imbalanced regression: A case study on vineyards
- Open Access
CMAViT: Integrating Climate, Managment, and Remote Sensing Data for Crop Yield Estimation with Multimodel Vision Transformers
Crop yield prediction is essential for agricultural planning but remains challenging due to the complex interactions between weather, climate, and management practices. To address these challenges, we introduce a deep learning-based multi-model called Climate-Management Aware Vision Transformer (CMAViT), designed for pixel-level vineyard yield predictions. CMAViT integrates both spatial and temporal data by leveraging remote sensing imagery and short-term meteorological data, capturing the effects of growing season variations. Additionally, it incorporates management practices, which are represented in text form, using a cross-attention encoder to model their interaction with time-series data. This innovative multi-modal transformer tested on a large dataset from 2016-2019 covering 2,200 hectares and eight grape cultivars including more than 5 million vines, outperforms traditional models like UNet-ConvLSTM, excelling in spatial variability capture and yield prediction, particularly for extreme values in vineyards. CMAViT achieved an R2 of 0.84 and a MAPE of 8.22% on an unseen test dataset. Masking specific modalities lowered performance: excluding management practices, climate data, and both reduced R2 to 0.73, 0.70, and 0.72, respectively, and raised MAPE to 11.92%, 12.66%, and 12.39%, highlighting each modality's importance for accurate yield prediction. Code is available at https://github.com/plant-ai-biophysics-lab/CMAViT.
Open AccessCMAViT: Integrating Climate, Managment, and Remote Sensing Data for Crop Yield Estimation with Multimodel Vision Transformers
Crop yield prediction is essential for agricultural planning but remains challenging due to the complex interactions between weather, climate, and management practices. To address these challenges, we introduce a deep learning-based multi-model called Climate-Management Aware Vision Transformer (CMAViT), designed for pixel-level vineyard yield predictions. CMAViT integrates both spatial and temporal data by leveraging remote sensing imagery and short-term meteorological data, capturing the effects of growing season variations. Additionally, it incorporates management practices, which are represented in text form, using a cross-attention encoder to model their interaction with time-series data. This innovative multi-modal transformer tested on a large dataset from 2016-2019 covering 2,200 hectares and eight grape cultivars including more than 5 million vines, outperforms traditional models like UNet-ConvLSTM, excelling in spatial variability capture and yield prediction, particularly for extreme values in vineyards. CMAViT achieved an R2 of 0.84 and a MAPE of 8.22% on an unseen test dataset. Masking specific modalities lowered performance: excluding management practices, climate data, and both reduced R2 to 0.73, 0.70, and 0.72, respectively, and raised MAPE to 11.92%, 12.66%, and 12.39%, highlighting each modality's importance for accurate yield prediction. Code is available at https://github.com/plant-ai-biophysics-lab/CMAViT.
- 27 July 2023
- Published by Walter de Gruyter GmbH
- p. 955-961
Relationships between freeze damaged vines and imagery from satellites and unmanned aerial vehicles in California vineyards
Precision agriculture is a reality in agriculture and is playing a key role as the industry comes to terms with the environment, market forces, quality requirements, traceability, vehicle guidance ...
- 27 July 2023
- Published by Walter de Gruyter GmbH
- p. 955-961
Relationships between freeze damaged vines and imagery from satellites and unmanned aerial vehicles in California vineyards
Precision agriculture is a reality in agriculture and is playing a key role as the industry comes to terms with the environment, market forces, quality requirements, traceability, vehicle guidance ...
- Open Access
- 28 March 2022
- Published by Hindawi Limited in Australian Journal of Grape and Wine Research
- Vol. 28 (4) , 522-533
Facilitating mapping and understanding of within‐vineyard variation in fruit composition using data pooled from multiple vineyards
- 28 March 2022
- Published by Hindawi Limited in Australian Journal of Grape and Wine Research
- Vol. 28 (4) , 522-533
Open AccessFacilitating mapping and understanding of within‐vineyard variation in fruit composition using data pooled from multiple vineyards
- Open Access
- 27 February 2022
- Published by Wiley in Australian Journal of Grape and Wine Research
- Vol. 28 (3) , 407-423
Characterising spatio‐temporal variation in fruit composition for improved winegrowing management in California Cabernet Sauvignon
- 27 February 2022
- Published by Wiley in Australian Journal of Grape and Wine Research
- Vol. 28 (3) , 407-423
Open AccessCharacterising spatio‐temporal variation in fruit composition for improved winegrowing management in California Cabernet Sauvignon
- Open Access
- 24 February 2022
- Published by American Society for Enology and Viticulture in American Journal of Enology and Viticulture
- Vol. 73 (2) , 93-105
Remote Sensing, Yield, Physical Characteristics, and Fruit Composition Variability in Cabernet Sauvignon Vineyards
Soil texture, topographical data, fruit zone light measurements, yield components, and fruit composition data were taken from 125 locations in each of four Vitis vinifera L. cv. Cabernet Sauvignon vineyards in the Lodi region of California during the 2017, 2018, and 2019 seasons. Data were compared against three sources of normalized difference vegetation index (NDVI) with different spatial resolutions: Landsat 8 (LS8NDVI; 30 m), Sentinel-2 (S2NDVI; 10 m), and manned aircraft with the interrow removed (HRNDVI; 20 cm). The manned aircraft also captured canopy temperature derived from infrared (thermal) wavelengths (HRCT; 40 cm) for additional comparisons. HRNDVI was inversely related to HRCT, as well as to several chemical components of fruit composition including tannins and anthocyanins. While some constituents of fruit composition such as anthocyanins may be related to NDVI, canopy temperature, and/or indirect measurements collected in the field, results presented here suggest that yield and fruit composition have a strong seasonal response and therefore environmental conditions should be considered if more accurate predictions are desired. Further, freely available public satellite data sources with mixed canopy and interrow pixels, such as Sentinel-2 and Landsat 8, provided similar information related to predicting specific fruit composition parameters compared to higher resolution imagery from contracted manned aircraft, from which the interrow signal was removed. Growers and wineries interested in predicting fruit composition that accounts for spatial variability may be able to conserve resources by using publicly available imagery sources and small numbers of targeted samples to achieve this goal.
- 24 February 2022
- Published by American Society for Enology and Viticulture in American Journal of Enology and Viticulture
- Vol. 73 (2) , 93-105
Open AccessRemote Sensing, Yield, Physical Characteristics, and Fruit Composition Variability in Cabernet Sauvignon Vineyards
Soil texture, topographical data, fruit zone light measurements, yield components, and fruit composition data were taken from 125 locations in each of four Vitis vinifera L. cv. Cabernet Sauvignon vineyards in the Lodi region of California during the 2017, 2018, and 2019 seasons. Data were compared against three sources of normalized difference vegetation index (NDVI) with different spatial resolutions: Landsat 8 (LS8NDVI; 30 m), Sentinel-2 (S2NDVI; 10 m), and manned aircraft with the interrow removed (HRNDVI; 20 cm). The manned aircraft also captured canopy temperature derived from infrared (thermal) wavelengths (HRCT; 40 cm) for additional comparisons. HRNDVI was inversely related to HRCT, as well as to several chemical components of fruit composition including tannins and anthocyanins. While some constituents of fruit composition such as anthocyanins may be related to NDVI, canopy temperature, and/or indirect measurements collected in the field, results presented here suggest that yield and fruit composition have a strong seasonal response and therefore environmental conditions should be considered if more accurate predictions are desired. Further, freely available public satellite data sources with mixed canopy and interrow pixels, such as Sentinel-2 and Landsat 8, provided similar information related to predicting specific fruit composition parameters compared to higher resolution imagery from contracted manned aircraft, from which the interrow signal was removed. Growers and wineries interested in predicting fruit composition that accounts for spatial variability may be able to conserve resources by using publicly available imagery sources and small numbers of targeted samples to achieve this goal.
- 8 July 2019
- Published by Walter de Gruyter GmbH
- p. 743-749
Can mapping of within-vineyard variability be facilitated using data from multiple vineyards?
- 8 July 2019
- Published by Walter de Gruyter GmbH
- p. 743-749
Can mapping of within-vineyard variability be facilitated using data from multiple vineyards?
- Open Access
- 1 September 2018
- Published by American Meteorological Society in Bulletin of the American Meteorological Society
- Vol. 99 (9) , 1791-1812
The Grape Remote Sensing Atmospheric Profile and Evapotranspiration Experiment
Particularly in light of California’s recent multiyear drought, there is a critical need for accurate and timely evapotranspiration (ET) and crop stress information to ensure long-term sustainability of high-value crops. Providing this information requires the development of tools applicable across the continuum from subfield scales to improve water management within individual fields up to watershed and regional scales to assess water resources at county and state levels. High-value perennial crops (vineyards and orchards) are major water users, and growers will need better tools to improve water-use efficiency to remain economically viable and sustainable during periods of prolonged drought. To develop these tools, government, university, and industry partners are evaluating a multiscale remote sensing–based modeling system for application over vineyards. During the 2013–17 growing seasons, the Grape Remote Sensing Atmospheric Profile and Evapotranspiration eXperiment (GRAPEX) project has collected micrometeorological and biophysical data within adjacent pinot noir vineyards in the Central Valley of California. Additionally, each year ground, airborne, and satellite remote sensing data were collected during intensive observation periods (IOPs) representing different vine phenological stages. An overview of the measurements and some initial results regarding the impact of vine canopy architecture on modeling ET and plant stress are presented here. Refinements to the ET modeling system based on GRAPEX are being implemented initially at the field scale for validation and then will be integrated into the regional modeling toolkit for large area assessment.
- 1 September 2018
- Published by American Meteorological Society in Bulletin of the American Meteorological Society
- Vol. 99 (9) , 1791-1812
Open AccessThe Grape Remote Sensing Atmospheric Profile and Evapotranspiration Experiment
Particularly in light of California’s recent multiyear drought, there is a critical need for accurate and timely evapotranspiration (ET) and crop stress information to ensure long-term sustainability of high-value crops. Providing this information requires the development of tools applicable across the continuum from subfield scales to improve water management within individual fields up to watershed and regional scales to assess water resources at county and state levels. High-value perennial crops (vineyards and orchards) are major water users, and growers will need better tools to improve water-use efficiency to remain economically viable and sustainable during periods of prolonged drought. To develop these tools, government, university, and industry partners are evaluating a multiscale remote sensing–based modeling system for application over vineyards. During the 2013–17 growing seasons, the Grape Remote Sensing Atmospheric Profile and Evapotranspiration eXperiment (GRAPEX) project has collected micrometeorological and biophysical data within adjacent pinot noir vineyards in the Central Valley of California. Additionally, each year ground, airborne, and satellite remote sensing data were collected during intensive observation periods (IOPs) representing different vine phenological stages. An overview of the measurements and some initial results regarding the impact of vine canopy architecture on modeling ET and plant stress are presented here. Refinements to the ET modeling system based on GRAPEX are being implemented initially at the field scale for validation and then will be integrated into the regional modeling toolkit for large area assessment.