Crop Growth Simulation Modeling

Bhatia, A. K.

doi:10.1007/978-3-319-05657-9_15

Cited by 9 publications

(9 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although these methods perform better since various types of inputs are fused, the acquisition of the required data is feasible at smaller scales such as farmlevel. Acquisition of data poses an essential limitation when larger scale areas are considered because of the cost of producing such high-resolution and accurate data at that scale [1,10,11].…”

Section: Introductionmentioning

confidence: 99%

Impact of large kernel size on yield prediction: a case study of corn yield prediction with SEDLA in the U.S. Corn Belt

Terliksiz,

Altilar

2024

Environ. Res. Commun.

View full text Add to dashboard Cite

Predicting agricultural yields is imperative for effective planning to sustain the growing global population. Traditionally, regression-based, simulation-based, and hybrid methods were employed for yield prediction. In recent times, there has been a notable shift towards the adoption of Machine Learning (ML) methods, with Deep Learning (DL), particularly Convolutional Neural Networks (CNNs) and Long-Short Term Memory (LSTM) networks, emerging as popular choices for their enhanced predictive accuracy. This research introduces a cost-effective DL architecture tailored for corn yield prediction, considering computational efficiency in processing time, data size, and NN architecture complexity. The proposed architecture, named SEDLA (Simple and Efficient Deep Learning Architecture), leverages the spatial and temporal learning capabilities of CNNs and LSTMs, respectively, with a unique emphasis on exploring the impact of kernel size in CNNs. Simultaneously, the study aims to exclusively employ satellite and yield data, strategically minimizing input variables to enhance the model's simplicity and efficiency. Notably, the study demonstrates that employing larger kernel sizes in CNNs, especially when processing histogram-based Surface Reflectance (SR) and Land Surface Temperature (LST) data from Moderate Resolution Imaging Spectroradiometer (MODIS), allows for a reduction in the number of hidden layers. The efficacy of the architecture was evaluated through extensive testing on corn yield prediction across 13 states in the United States (U.S.) Corn Belt at county-level. The experimental results showcase the superiority of the proposed architecture, achieving a Mean Absolute Percentage Error (MAPE) of 6.71 and Root Mean Square Error (RMSE) of 14.34, utilizing a single-layer CNN with a 15x15 kernel in conjunction with LSTM. These outcomes surpass existing benchmarks in the literature, affirming the efficacy and potential of the suggested DL framework for accurate and efficient crop yield predictions.

show abstract

Section: Introductionmentioning

confidence: 99%

Impact of large kernel size on yield prediction: a case study of corn yield prediction with SEDLA in the U.S. Corn Belt

Terliksiz,

Altilar

2024

Environ. Res. Commun.

View full text Add to dashboard Cite

show abstract

“…In a review study of agricultural practices in [4], the authors describe that a "major limitation of crop growth models is the lack of spatial information on the actual conditions of each field or region". A more extensive list of shortcomings is provided in [5], where the authors state that "the main limitations of crop growth models are the cost of obtaining the necessary input data to run the model, the lack of spatial information", and "the input data quality".…”

Section: Introductionmentioning

confidence: 99%

Yield Prediction for Winter Wheat with Machine Learning Models Using Sentinel-1, Topography, and Weather Data

Bogdanovski

Svenningsson

Månsson³

et al. 2023

Agriculture

View full text Add to dashboard Cite

We train and compare the performance of two different machine learning algorithms to learn changes in winter wheat production for fields from the southwest of Sweden. As input to these algorithms, we use cloud-penetrating Sentinel-1 polarimetry radar data together with respective field topography and local weather over four different years. We note that all of the input data were freely available. During training, we used information on winter wheat production over the fields of interest which was available from participating farmers. The two machine learning models we trained are the Light Gradient-Boosting Machine and a Feed-forward Neural Network. Our results show that Sentinel-1 data contain valuable information which can be used for training to predict winter wheat yield once two important steps are taken: performing a critical transformation of each pixel in the images to align it to the training data and then following up with despeckling treatment. Using this approach, we were able to achieve a top root mean square error of 0.75 tons per hectare and a top accuracy of 86% using a k-fold method with k=5. More importantly, however, we established that Sentinel-1 data alone are sufficient to predict yield with an average root mean square error of 0.89 tons per hectare, making this method feasible to employ worldwide.

show abstract

“…The traditional approaches to estimating crop phenology have been through ground observations and the use of crop models (e.g., Simple and Universal CROp growth Simulator (SUCROS) [12], Hybrid-Corn [14], WOrld FOod STudies (WOFOST) [13][14][15]). The crop models can estimate crop growth dates with a high level of accuracy [root mean square error (RMSE): 0-4 days], but they require a number of detailed information inputs such as crop (e.g., cultivar used and plant population), weather (e.g., temperature, rainfall, solar radiation and wind speed) conditions [14,16] and soil (e.g., initial soil moisture). On the one hand, the use of these crop models is usually limited by the availability of the required data inputs; on the other hand, the models need to be calibrated for particular species and site-specific conditions based on ground data [11,16], and the ground observations collected by observers are not cost-efficient.…”

Section: Introductionmentioning

confidence: 99%

“…The crop models can estimate crop growth dates with a high level of accuracy [root mean square error (RMSE): 0-4 days], but they require a number of detailed information inputs such as crop (e.g., cultivar used and plant population), weather (e.g., temperature, rainfall, solar radiation and wind speed) conditions [14,16] and soil (e.g., initial soil moisture). On the one hand, the use of these crop models is usually limited by the availability of the required data inputs; on the other hand, the models need to be calibrated for particular species and site-specific conditions based on ground data [11,16], and the ground observations collected by observers are not cost-efficient. Accordingly, the traditional methods are sitespecific and typically cannot monitor crop phenology beyond the field scale over larger areas [11].…”

Section: Introductionmentioning

confidence: 99%

A Study on Phenology Detection of Corn in Northeastern China with Fused Remote Sensing Data

Zeng¹,

Xiang²

2018

Recent Advances and Applications in Remote Sensing

View full text Add to dashboard Cite

Accurate phenology information detection is the basis for other remote-sensing based agriculture applications. So far, there have been a lot of phenology estimation models based on remote-sensing data, but little attention was paid to microscopic mechanism of crops and the environmental factors. The main purpose of this chapter is to apply a new phenology detection model, which combined physical mechanism-based crop models with remote-sensing data to detect the critical phenological stages of corn in Northeast China (Jilin and Liaoning Provinces). Compared to the phenology observations from the agriculture meteorological stations, the corn phenology estimation accuracy in Northeast China using only MODIS data is much lower than that in the US field sites. The main reason might be the small size of single piece of cropland in northeastern China, which led to the mixed MODIS pixels. Accordingly, Landsat and MODIS data fusion methods were applied to get time-series images with Landsat-like spatial resolution and MODISlike temporal resolution, and quantitative and qualitative validation was conducted to evaluate and verify the accuracy of the data fusion. The results show that data fusion of Landsat and MODIS improved the spatial resolution and decreased the influence of mixed pixels.

show abstract

Crop Growth Simulation Modeling

Cited by 9 publications

References 25 publications

Impact of large kernel size on yield prediction: a case study of corn yield prediction with SEDLA in the U.S. Corn Belt

Impact of large kernel size on yield prediction: a case study of corn yield prediction with SEDLA in the U.S. Corn Belt

Yield Prediction for Winter Wheat with Machine Learning Models Using Sentinel-1, Topography, and Weather Data

A Study on Phenology Detection of Corn in Northeastern China with Fused Remote Sensing Data

Contact Info

Product

Resources

About