Field-scale crop yield prediction using multi-temporal WorldView-3 and PlanetScope satellite data and deep learning

Sagan, Vasit; Maimaitijiang, Maitiniyazi; Bhadra, Sourav; Maimaitiyiming, Matthew; Brown, Davis R.; Sidike, Paheding; Fritschi, Felix B.

doi:10.1016/j.isprsjprs.2021.02.008

Cited by 112 publications

(63 citation statements)

References 102 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although You et al used raw satellite image data, they also condensed it using pixel value histograms. As well as to investigate the use of raw images, Sagan et al also did experiments based on several handcrafted features, such as vegetation indices [22]. The researchers used the images collected from each plot for two main directions in their study: (1) condense them into handcrafted vegetation indices, and (2) use the raw images directly in a CNN-based model.…”

Section: Machine Learning Applied To Remotely Sensed Datamentioning

confidence: 99%

“…As crop yield statistics required to make predictions based on farm or field-scale have not commonly been available to the public [4]. Sagan et al [22] made an effort to predict field-scale crop yields using deep learning by building a dataset comprising small experimental plots and making yield predictions for these plots. The results show the models can learn growth-related features, even on such small plots.…”

Section: Machine Learning Applied To Remotely Sensed Datamentioning

confidence: 99%

“…Using satellite images is the current state-of-the-art for farm-scale crop yield prediction with no intrusive and labour-intensive monitoring, as described in [8,9,22]. Therefore, it is also a significant focus of this research study.…”

Section: Satellite Image Datamentioning

confidence: 99%

“…Therefore, it is also a significant focus of this research study. Building a dataset of multispectral satellite images for farm-scale crop yield predictions relies on the availability of high-resolution satellite images combined with precise geographical information about farms [22]. Therefore, the Copernicus Sentinel-2 satellite mission is the source of all images used in this research study.…”

Section: Satellite Image Datamentioning

confidence: 99%

“…To the best of our knowledge, no prior work predicts real-world farm-scale crop yields on a large scale, making it difficult to compare our results with the current state-of-theart [22] crop yield predictions. Sharma et al [8] predict wheat yield at a tehsil scale, a small administrative unit in India and achieve an RMSE of between 4.8 and 33 kg/1000 m 2 when trained in different states in India.…”

Section: Predictions As Regional Analyticsmentioning

confidence: 99%

See 4 more Smart Citations

Farm-Scale Crop Yield Prediction from Multi-Temporal Data Using Deep Hybrid Neural Networks

et al. 2021

View full text Add to dashboard Cite

Farm-scale crop yield prediction is a natural development of sustainable agriculture, producing a rich amount of food without depleting and polluting environmental resources. Recent studies on crop yield production are limited to regional-scale predictions. The regional-scale crop yield predictions usually face challenges in capturing local yield variations based on farm management decisions and the condition of the field. For this research, we identified the need to create a large and reusable farm-scale crop yield production dataset, which could provide precise farm-scale ground-truth prediction targets. Therefore, we utilise multi-temporal data, such as Sentinel-2 satellite images, weather data, farm data, grain delivery data, and cadastre-specific data. We introduce a deep hybrid neural network model to train this multi-temporal data. This model combines the features of convolutional layers and recurrent neural networks to predict farm-scale crop yield production across Norway. The proposed model could efficiently make the target predictions with the mean absolute error of 76 kg per 1000 m2. In conclusion, the reusable farm-scale multi-temporal crop yield dataset and the proposed novel model could meet the actual requirements for the prediction targets in this paper, providing further valuable insights for the research community.

show abstract

Section: Machine Learning Applied To Remotely Sensed Datamentioning

confidence: 99%

Section: Machine Learning Applied To Remotely Sensed Datamentioning

confidence: 99%

Section: Satellite Image Datamentioning

confidence: 99%

Section: Satellite Image Datamentioning

confidence: 99%

Section: Predictions As Regional Analyticsmentioning

confidence: 99%

See 3 more Smart Citations

Farm-Scale Crop Yield Prediction from Multi-Temporal Data Using Deep Hybrid Neural Networks

et al. 2021

View full text Add to dashboard Cite

show abstract

Leveraging soil mapping and machine learning to improve spatial adjustments in plant breeding trials

Carroll,

Riera,

Miller

et al. 2024

Crop Science

View full text Add to dashboard Cite

Spatial adjustments are used to improve the estimate of plot seed yield across crops and geographies. Moving means (MM) and P‐Spline are examples of spatial adjustment methods used in plant breeding trials to deal with field heterogeneity. Within the trial, spatial variability primarily comes from soil feature gradients, such as nutrients, but a study of the importance of various soil factors including nutrients is lacking. We analyzed plant breeding progeny row (PR) and preliminary yield trial (PYT) data of a public soybean breeding program across 3 years consisting of 43,545 plots. We compared several spatial adjustment methods: unadjusted (as a control), MM adjustment, P‐spline adjustment, and a machine learning‐based method called XGBoost. XGBoost modeled soil features at: (a) the local field scale for each generation and per year, and (b) all inclusive field scale spanning all generations and years. We report the usefulness of spatial adjustments at both PR and PYT stages of field testing and additionally provide ways to utilize interpretability insights of soil features in spatial adjustments. Our work shows that using soil features for spatial adjustments increased the relative efficiency by 81%, reduced the similarity of selection by 30%, and reduced the Moran's I from 0.13 to 0.01 on average across all experiments. These results empower breeders to further refine selection criteria to make more accurate selections and select for macro‐ and micro‐nutrients stress tolerance.

show abstract

Machine Learning Approaches for Crop Identification from Remote Sensing Imagery: A Review

Wu¹,

Maleki²,

Oubara³

et al. 2023

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Field-scale crop yield prediction using multi-temporal WorldView-3 and PlanetScope satellite data and deep learning

Cited by 112 publications

References 102 publications

Farm-Scale Crop Yield Prediction from Multi-Temporal Data Using Deep Hybrid Neural Networks

Farm-Scale Crop Yield Prediction from Multi-Temporal Data Using Deep Hybrid Neural Networks

Leveraging soil mapping and machine learning to improve spatial adjustments in plant breeding trials

Machine Learning Approaches for Crop Identification from Remote Sensing Imagery: A Review

Contact Info

Product

Resources

About