Effects of Satellite Revisit Rate and Time-Series Smoothing Method on Throughout-Season Maize Yield Correlation Accuracy

Myers, Emily; Kerekes, John P.; Daughtry, Craig S. T.; Russ, Andrew L.

doi:10.1109/jstars.2021.3129148

Cited by 4 publications

(2 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Integrating physiological and environmental variables, process-based models simulate crop growth process. These models use mathematical equations to represent the growth processes of plants and to simulate their response to various inputs& scenarios via use of 3-D Convolutional Neural Networks (3D CNN) [17,18,19,20]. Models such as CERES, DSSAT, and APSIM are examples.…”

Section: Models Based On Processmentioning

confidence: 99%

Devising of an Efficient Multi-parametric System for Prediction of Crop Yield using Augmented Incremental Machine & Deep Learning Operations

2024

Journal of Electrical Systems

View full text Add to dashboard Cite

Agricultural research and management have become increasingly dependent on accurate crop yield forecasting. This paper introduces a comprehensive model that incorporates multiple parameters to predict crop yield with high levels of precision and accuracy. The applications of this research are extensive and consequential. Accurate crop yield forecasts can assist farmers, agronomists, and policymakers with resource allocation, crop selection, and land management decisions. Our model provides valuable insights for optimizing agricultural practices and increasing overall productivity by taking into account key factors such as weather, soil type and fertility, crop variety, farming practices, genetics, satellite imagery & samples. The proposed model contains several internal components, each of which serves an efficient set of distinct functions. Deep Q Learning is used to analyze the impact of weather on crop variety, allowing the model to account for the impact of precipitation, temperature, humidity, Sunlight, and resistance to pests and diseases. Deep Dyna Q Classifier is used to evaluate the impact of soil type, fertility, and farming practices, thus accounting for variations in nutrient availability, irrigation, fertilization, and pest pressure. The crop's genetics are evaluated using Auto Encoders and a VARMA Model, which take into account the impact of inherent traits on productivity. Moreover, relevant spatial information sets are extracted from satellite images using a ResNet101 Model process. The rationale for integrating these internal components is based on their individual strengths and their capacity to capture complex interactions between various parameters. Our model achieves exceptional performance through the utilization of deep learning, reinforcement learning, and statistical modelling. For predicting the yield of Mango, Cotton, Wheat, Bajra, and Rice Paddy crops, the experimental results demonstrate a remarkable AUC of 99.2%, precision exceeding 99.5%, accuracy of 99.8%, recall of 99.4%, and an impressive AUC of 99.2%. In conclusion, our multi-parametric engine provides a robust and effective method for predicting crop yield. Its superior performance is a result of its ability to seamlessly integrate multiple data sources and employ advanced deep learning techniques. This research paves the way for informed agricultural decisionmaking, allowing stakeholders to optimize resource allocation, boost productivity, and ultimately contribute to food security and sustainability levels.

show abstract

Section: Models Based On Processmentioning

confidence: 99%

Devising of an Efficient Multi-parametric System for Prediction of Crop Yield using Augmented Incremental Machine & Deep Learning Operations

2024

Journal of Electrical Systems

View full text Add to dashboard Cite

show abstract

“…Furthermore, monitoring yield forecasts throughout the growing season informs farmers management decisions like fertilization rates, irrigation events, pest control, and disease management. [1][2][3] Maize is the world's most popularly grown crop, accounting for approximately one third of globally harvested food crops. 4 Much effort therefore has been expended on developing accurate and scalable yield forecasting models.…”

Section: Introductionmentioning

confidence: 99%

A comparison of traditional and machine learning corn yield models using hyperspectral UAS and Landsat imagery

Burglewski,

Ketterings,

Shajahan

et al. 2023

Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imaging XXIX

View full text Add to dashboard Cite

The operationalization of precision agriculture imaging-based systems, especially in staple crops like maize (Zea mays L.), requires a quantitative comparison of yield forecast approaches toward improved crop management. Here, we compare the implementation of linear and exponential based sileage yield models for maize to machinelearning (ML) based yield models utilizing spaceborne multispectral imagery (MSI) and unmanned aerial system (UAS) collected hyperspectral imagery (HSI), respectively. We collected UAS imagery in a maize field in upstate New York at the V10 growth stage using a Headwall Nano-Hyperspec 272-band visible and near-infrared imaging system to test the accuracy a feed forward neural network yield estimation regression model as well as a support vector regression (SVR). Landsat imagery of the same field was collected over ten separate instances throughout the season for use in linear and exponential regressions, while ground truth sileage yield data were provided by an on-board yield monitor during harvest. The neural network regression response induced between 4.6-13% mean absolute error (MAE), the linear and exponential regression yielded a best performance of 5.5%, while the SVR model ranged from 1.16-4.56% MAE. These results bode well for future implementation of such silage maize yield modeling approaches leveraging hyperspectral data that include the spectral red edge. However, we suggest that model efficacy should be evaluated for use in other regions.

show abstract

CYPBL: Crop Yield Prediction using Bi-Directional LSTM under PySpark interface

Chaudhary,

Pathak

2024

Multimed Tools Appl

View full text Add to dashboard Cite

Effects of Satellite Revisit Rate and Time-Series Smoothing Method on Throughout-Season Maize Yield Correlation Accuracy

Cited by 4 publications

References 40 publications

Devising of an Efficient Multi-parametric System for Prediction of Crop Yield using Augmented Incremental Machine & Deep Learning Operations

Devising of an Efficient Multi-parametric System for Prediction of Crop Yield using Augmented Incremental Machine & Deep Learning Operations

A comparison of traditional and machine learning corn yield models using hyperspectral UAS and Landsat imagery

CYPBL: Crop Yield Prediction using Bi-Directional LSTM under PySpark interface

Contact Info

Product

Resources

About