Rob Strey
Research Subjects
Rob Strey has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- David B. Lobell
Department of Earth System Science, Stanford University, Stanford, USA
3 shared publications - Sherrie Wang
Massachusetts Institute of Technology
3 shared publications - Stefania Di Tommaso
Center on Food Security and the Environment, Stanford University, Stanford, CA 94305, United States of America
2 shared publications - Alexander Kennepohl
Progressive Environmental & Agricultural Technologies, 10435 Berlin, Germany
1 shared publication - Anjuli Jain Figueroa
Woods Institute for the Environment, Stanford University, Stanford, CA 94305, USA
1 shared publication - Joey Faulkner
Progressive Environmental & Agricultural Technologies, 10435 Berlin, Germany
1 shared publication
Latest Publications
- Open Access
- 22 August 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (17) , 4123
Annual Field-Scale Maps of Tall and Short Crops at the Global Scale Using GEDI and Sentinel-2
Crop type maps are critical for tracking agricultural land use and estimating crop production. Remote sensing has proven an efficient and reliable tool for creating these maps in regions with abundant ground labels for model training, yet these labels remain difficult to obtain for many regions and years. NASA’s Global Ecosystem Dynamics Investigation (GEDI) spaceborne LiDAR instrument, originally designed for forest monitoring, has shown promise for distinguishing tall and short crops. In the current study, we leverage GEDI to develop wall-to-wall maps of short vs. tall crops on a global scale at 10 m resolution for 2019–2021. Specifically, we show that (i) GEDI returns can reliably be classified into tall and short crops after removing shots with extreme view angles or topographic slope, (ii) the frequency of tall crops over time can be used to identify months when tall crops are at their peak height, and (iii) GEDI shots in these months can then be used to train random forest models that use Sentinel-2 time series to accurately predict short vs. tall crops. Independent reference data from around the world are then used to evaluate these GEDI-S2 maps. We find that GEDI-S2 performed nearly as well as models trained on thousands of local reference training points, with accuracies of at least 87% and often above 90% throughout the Americas, Europe, and East Asia. A systematic underestimation of tall crop area was observed in regions where crops frequently exhibit low biomass, namely Africa and South Asia, and further work is needed in these systems. Although the GEDI-S2 approach only differentiates tall from short crops, in many landscapes this distinction is sufficient to map individual crop types (e.g., maize vs. soy, sugarcane vs. rice). The combination of GEDI and Sentinel-2 thus presents a very promising path towards global crop mapping with minimal reliance on ground data.
- 22 August 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (17) , 4123
Open AccessAnnual Field-Scale Maps of Tall and Short Crops at the Global Scale Using GEDI and Sentinel-2
Crop type maps are critical for tracking agricultural land use and estimating crop production. Remote sensing has proven an efficient and reliable tool for creating these maps in regions with abundant ground labels for model training, yet these labels remain difficult to obtain for many regions and years. NASA’s Global Ecosystem Dynamics Investigation (GEDI) spaceborne LiDAR instrument, originally designed for forest monitoring, has shown promise for distinguishing tall and short crops. In the current study, we leverage GEDI to develop wall-to-wall maps of short vs. tall crops on a global scale at 10 m resolution for 2019–2021. Specifically, we show that (i) GEDI returns can reliably be classified into tall and short crops after removing shots with extreme view angles or topographic slope, (ii) the frequency of tall crops over time can be used to identify months when tall crops are at their peak height, and (iii) GEDI shots in these months can then be used to train random forest models that use Sentinel-2 time series to accurately predict short vs. tall crops. Independent reference data from around the world are then used to evaluate these GEDI-S2 maps. We find that GEDI-S2 performed nearly as well as models trained on thousands of local reference training points, with accuracies of at least 87% and often above 90% throughout the Americas, Europe, and East Asia. A systematic underestimation of tall crop area was observed in regions where crops frequently exhibit low biomass, namely Africa and South Asia, and further work is needed in these systems. Although the GEDI-S2 approach only differentiates tall from short crops, in many landscapes this distinction is sufficient to map individual crop types (e.g., maize vs. soy, sugarcane vs. rice). The combination of GEDI and Sentinel-2 thus presents a very promising path towards global crop mapping with minimal reliance on ground data.
- Open Access
- 2 February 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (3) , 703
Mapping Sugarcane in Central India with Smartphone Crowdsourcing
In India, the second-largest sugarcane producing country in the world, accurate mapping of sugarcane land is a key to designing targeted agricultural policies. Such a map is not available, however, as it is challenging to reliably identify sugarcane areas using remote sensing due to sugarcane’s phenological characteristics, coupled with a range of cultivation periods for different varieties. To produce a modern sugarcane map for the Bhima Basin in central India, we utilized crowdsourced data and applied supervised machine learning (neural network) and unsupervised classification methods individually and in combination. We highlight four points. First, smartphone crowdsourced data can be used as an alternative ground truth for sugarcane mapping but requires careful correction of potential errors. Second, although the supervised machine learning method performs best for sugarcane mapping, the combined use of both classification methods improves sugarcane mapping precision at the cost of worsening sugarcane recall and missing some actual sugarcane area. Third, machine learning image classification using high-resolution satellite imagery showed significant potential for sugarcane mapping. Fourth, our best estimate of the sugarcane area in the Bhima Basin is twice that shown in government statistics. This study provides useful insights into sugarcane mapping that can improve the approaches taken in other regions.
- 2 February 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (3) , 703
Open AccessMapping Sugarcane in Central India with Smartphone Crowdsourcing
In India, the second-largest sugarcane producing country in the world, accurate mapping of sugarcane land is a key to designing targeted agricultural policies. Such a map is not available, however, as it is challenging to reliably identify sugarcane areas using remote sensing due to sugarcane’s phenological characteristics, coupled with a range of cultivation periods for different varieties. To produce a modern sugarcane map for the Bhima Basin in central India, we utilized crowdsourced data and applied supervised machine learning (neural network) and unsupervised classification methods individually and in combination. We highlight four points. First, smartphone crowdsourced data can be used as an alternative ground truth for sugarcane mapping but requires careful correction of potential errors. Second, although the supervised machine learning method performs best for sugarcane mapping, the combined use of both classification methods improves sugarcane mapping precision at the cost of worsening sugarcane recall and missing some actual sugarcane area. Third, machine learning image classification using high-resolution satellite imagery showed significant potential for sugarcane mapping. Fourth, our best estimate of the sugarcane area in the Bhima Basin is twice that shown in government statistics. This study provides useful insights into sugarcane mapping that can improve the approaches taken in other regions.
- Open Access
- 11 September 2020
- Published by MDPI AG in Remote Sensing
- Vol. 12 (18) , 2957
Mapping Crop Types in Southeast India with Smartphone Crowdsourcing and Deep Learning
High resolution satellite imagery and modern machine learning methods hold the potential to fill existing data gaps in where crops are grown around the world at a sub-field level. However, high resolution crop type maps have remained challenging to create in developing regions due to a lack of ground truth labels for model development. In this work, we explore the use of crowdsourced data, Sentinel-2 and DigitalGlobe imagery, and convolutional neural networks (CNNs) for crop type mapping in India. Plantix, a free app that uses image recognition to help farmers diagnose crop diseases, logged 9 million geolocated photos from 2017–2019 in India, 2 million of which are in the states of Andhra Pradesh and Telangana in India. Crop type labels based on farmer-submitted images were added by domain experts and deep CNNs. The resulting dataset of crop type at coordinates is high in volume, but also high in noise due to location inaccuracies, submissions from out-of-field, and labeling errors. We employed a number of steps to clean the dataset, which included training a CNN on very high resolution DigitalGlobe imagery to filter for points that are within a crop field. With this cleaned dataset, we extracted Sentinel time series at each point and trained another CNN to predict the crop type at each pixel. When evaluated on the highest quality subset of crowdsourced data, the CNN distinguishes rice, cotton, and “other” crops with 74% accuracy in a 3-way classification and outperforms a random forest trained on harmonic regression features. Furthermore, model performance remains stable when low quality points are introduced into the training set. Our results illustrate the potential of non-traditional, high-volume/high-noise datasets for crop type mapping, some improvements that neural networks can achieve over random forests, and the robustness of such methods against moderate levels of training set noise. Lastly, we caution that obstacles like the lack of good Sentinel-2 cloud mask, imperfect mobile device location accuracy, and preservation of privacy while improving data access will need to be addressed before crowdsourcing can widely and reliably be used to map crops in smallholder systems.
- 11 September 2020
- Published by MDPI AG in Remote Sensing
- Vol. 12 (18) , 2957
Open AccessMapping Crop Types in Southeast India with Smartphone Crowdsourcing and Deep Learning
High resolution satellite imagery and modern machine learning methods hold the potential to fill existing data gaps in where crops are grown around the world at a sub-field level. However, high resolution crop type maps have remained challenging to create in developing regions due to a lack of ground truth labels for model development. In this work, we explore the use of crowdsourced data, Sentinel-2 and DigitalGlobe imagery, and convolutional neural networks (CNNs) for crop type mapping in India. Plantix, a free app that uses image recognition to help farmers diagnose crop diseases, logged 9 million geolocated photos from 2017–2019 in India, 2 million of which are in the states of Andhra Pradesh and Telangana in India. Crop type labels based on farmer-submitted images were added by domain experts and deep CNNs. The resulting dataset of crop type at coordinates is high in volume, but also high in noise due to location inaccuracies, submissions from out-of-field, and labeling errors. We employed a number of steps to clean the dataset, which included training a CNN on very high resolution DigitalGlobe imagery to filter for points that are within a crop field. With this cleaned dataset, we extracted Sentinel time series at each point and trained another CNN to predict the crop type at each pixel. When evaluated on the highest quality subset of crowdsourced data, the CNN distinguishes rice, cotton, and “other” crops with 74% accuracy in a 3-way classification and outperforms a random forest trained on harmonic regression features. Furthermore, model performance remains stable when low quality points are introduced into the training set. Our results illustrate the potential of non-traditional, high-volume/high-noise datasets for crop type mapping, some improvements that neural networks can achieve over random forests, and the robustness of such methods against moderate levels of training set noise. Lastly, we caution that obstacles like the lack of good Sentinel-2 cloud mask, imperfect mobile device location accuracy, and preservation of privacy while improving data access will need to be addressed before crowdsourcing can widely and reliably be used to map crops in smallholder systems.