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

Engen, Martin; Sandø, Erik; Sjølander, Benjamin Lucas Oscar; Arenberg, Simon; Gupta, Rashmi; Goodwin, Morten

doi:10.3390/agronomy11122576

Cited by 23 publications

(29 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since 2015, the Sentinel 2 satellites deliver imagery at high resolution (up to 10m). Several studies have used this data for regional crop yield modeling [49,12] and regional vegetation forecasting [14,64]. With EarthNet2021 [43], the first dataset for continental-scale satellite imagery forecasting was introduced.…”

Section: Related Workmentioning

confidence: 99%

Forecasting localized weather impacts on vegetation as seen from space with meteo-guided video prediction

Benson¹,

Requena-Mesa²,

Robin³

et al. 2023

Preprint

View full text Add to dashboard Cite

We present a novel approach for modeling vegetation response to weather in Europe as measured by the Sentinel 2 satellite. Existing satellite imagery forecasting approaches focus on photorealistic quality of the multispectral images, while derived vegetation dynamics have not yet received as much attention. We leverage both spatial and temporal context by extending state-of-the-art video prediction methods with weather guidance. We extend the EarthNet2021 dataset to be suitable for vegetation modeling by introducing a learned cloud mask and an appropriate evaluation scheme. Qualitative and quantitative experiments demonstrate superior performance of our approach over a wide variety of baseline methods, including leading approaches to satellite imagery forecasting. Additionally, we show how our modeled vegetation dynamics can be leveraged in a downstream task: inferring gross primary productivity for carbon monitoring. To the best of our knowledge, this work presents the first models for continental-scale vegetation modeling at fine resolution able to capture anomalies beyond the seasonal cycle, thereby paving the way for predictive assessments of vegetation status.

show abstract

Section: Related Workmentioning

confidence: 99%

Forecasting localized weather impacts on vegetation as seen from space with meteo-guided video prediction

Benson¹,

Requena-Mesa²,

Robin³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Management in agriculture, from the micro-plot level to the farm level, benefits from the facilities offered by imaging and informatics in soil and agricultural crops' knowledge, planning of technological works, and specific interventions for obtaining economically efficient yields [51,52]. Estimating production using accessible and safe methods is of interest in relation to crop technologies and influencing factors, including harvesting, transport and production storage, products' market, and other segments in the agri-food chain [53][54][55].…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Different Methods and Models for Grass Cereals’ Production Estimation: Case Study in Wheat

Sala

Herbei²

2023

Agronomy

View full text Add to dashboard Cite

Adequate management of agricultural crops requires, among other things, accessible and sufficiently accurate methods for assessing plant nutrition and crop vegetation status and for agricultural production estimation. Sustainable technologies are based on correct decisions, prompt interventions and appropriate works, and correct information in real time, and the obtaining information methods can be simple, accessible, and appropriate in relation to different user categories (e.g., farmers, researchers, decision makers). This study used mineral fertilization (NPK), with 11 experimental variants, to ensure a controlled differentiated nutrition of the wheat plants, “Alex” cultivar. Regression analysis was used to obtain models in estimating wheat production, by methods based on: (a) NPK fertilizers applied (F) in the 11 experimental variants; (b) physiological indices (PI), represented by the chlorophyll content (Chl), and plant nutrition status on the experimental variants, in terms of macroelement content in the leaves, evaluated by foliar diagnosis (Nfd, Pfd, Kfd); (c) imaging analysis (IA) based on digital images of the wheat experimental variants, and calculated indices. A set of models was obtained, with different precision levels and statistical safety: R2 = 0.763, p = 0.013 for the model based on applied fertilizers (NPKF); R2 = 0.883, p < 0.01 for the model based on foliar diagnosis (NPKfd); R2 = 0.857, p < 0.01 for the model based on chlorophyll content (Chl); R2 = 0.975, p < 0.01 for the model based on normalized rgb color parameters (RGB color system); R2 = 0.925, p < 0.01 for the model based on the DGCI calculated index. The model based on applied fertilizers (F model) was tested in relation to wheat production data, for a period of six years, communicated by other studies. Fit degree analysis between predicted yield based on the F model and real yield (six-year average) was confirmed by R2 = 0.717, compared to R2 = 0.763 for the F model in this study. The models obtained in this study, related to the “Alex” wheat cultivar, can be used for other studies, but with a certain margin of error, given the coefficient values, specific to the obtained equations. The approach concept, methods, and models presented can be opportunities for other studies to facilitate their comparative analysis, their adaptation, and/or development in the form of new models that are useful in different studies, research, or agricultural practices, for their integration into crop management strategies.

show abstract

“…These studies show us that crop yield and development are still dependent on many variables and have a complex structure (Schauberger et al, 2020). These prediction efforts have been conducted on a regional and large scale (Dang et al, 2021;Gómez et al, 2021) as well as on a field scale (Engen et al, 2021;Cao et al, 2021a) in diverse climates. To predict crop yield, crop growth simulation models (AquaCrop, DSSAT, WOFOST, EPIC, VIC, etc.)…”

Section: Introductionmentioning

confidence: 99%

Crop Yield Prediction based on Reanalysis and Crop Phenology Data in the Agroclimatic Zones

Yeșilköy¹,

Demir²

2023

Preprint

View full text Add to dashboard Cite

Crop yield and phenological stages are remarkably sensitive to not only environmental factors like atmospheric conditions and physical properties of soils but also agricultural activities. Accurate crop yield prediction plays a crucial role in food security and agricultural sustainability. There are several approaches that a wide range of researchers have tried to predict crop yield at different scales. In this study, we tested AgERA5 reanalysis product and crop phenological stage data to predict winter wheat yields in the agricultural lands of the agroclimatic regions of Turkey. The main objective is to propose a deep learning approach based on the combination of the reanalysis, which was extracted for the agricultural lands of the five most productive agroclimatic zones, and crop phenology data to predict winter wheat yields. Five performance indicators, such as normalized root mean squared error (NRMSE), mean absolute percentage error (MAPE), root mean squared error (RMSE), Nash-Sutcliffe Efficiency (NSE), and coefficient of determination (R2), are chosen to test the model’s accuracy and effectiveness. We have obtained promising findings and suggested that AgERA5 reanalysis data can be used as an input for the crop yield prediction of winter wheat with an error below 10% and a coefficient of determination above 0.9.

show abstract

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

Cited by 23 publications

References 41 publications

Forecasting localized weather impacts on vegetation as seen from space with meteo-guided video prediction

Forecasting localized weather impacts on vegetation as seen from space with meteo-guided video prediction

Evaluation of Different Methods and Models for Grass Cereals’ Production Estimation: Case Study in Wheat

Crop Yield Prediction based on Reanalysis and Crop Phenology Data in the Agroclimatic Zones

Contact Info

Product

Resources

About