Improving maize yield prediction at the county level from 2002 to 2015 in China using a novel deep learning approach

Li, Xingang; Geng, Hao; Zhang, Liqiang; Peng, Shuwen; Xin, Qi; Huang, Jianxi; Li, Xuecao; Liu, Suhong; Wang, Yuebin

doi:10.1016/j.compag.2022.107356

Cited by 19 publications

(7 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Results regarding the prediction of the corn crop production were communicated both in relation to the climatic conditions, as well as to the methods and techniques used, under statistical safety conditions (Maitah et al, 2021;Li et al, 2022).…”

Section: Resultsmentioning

confidence: 99%

Variation of Some Biometric Parameters in Corn Ears in Relation to Plant Status

KONYA,

HERBEI,

SALA

2023

LSSD

View full text Add to dashboard Cite

The study evaluated the variability of some plants and ears parameters in maize, and the possibility of estimating the productivity elements at the ear level depending on the plants status parameters. The study was done in the area of Sanmihaiu Roman, Timis County, Romania. The maize hybrid DKC 5075 was cultivated in a non-irrigated system, with an appropriate culture technology. The number of leaves during the vegetation period (Ln-v), the number of leaves at harvest (Ln-h) was evaluated, and the height of the plants (Ph) and the diameter of the plant stem (Pd) were also determined. Determinations were made regarding the length of the ear (El), the diameter of the ear (Ed), the weight of the ear (Ew) and the number of grains per ear (Gn). In the climatic conditions specific to the agricultural year 2021 - 2022, the variability recorded, based on the coefficient of variation (CV) at the level of the studied parameters, was: CVPh=30.4824 for plant height; CVPd=9.8659 for the diameter of the plant stem; CVLn-v=13.2348 for the number of leaves in vegetation; CVLn-v=23.1179 for the number of leaves at harvest; CVEl=12.3450 for the length of the ear; CVEd=10.9924 for the diameter of the ear; CVEw=23.5464 for the weight of the ear; CVGn=17.5084 for the number of grains per ear. Different correlations were recorded between parameters studied at the level of plants and maize ears. Interdependence relationships between the studied parameters were described by linear equations (e.g. Ew in relation to Ed) and polynomial equations (e.g. Ew in relation to Gn). The Ew variation was estimated in relation to Ph and Ln-v according to R2=0.713 (Multiple R=0.845), and in relation to Pd and Ln-v according to R2=0.730 (Multiple R=0.854). The variation of Gn was estimated in relation to Ph and Ln-v according to R2=0.856 (Multiple R=0.925). 3D models and as isoquants were obtained to graphically described the variation of the weight of the ears (Ew) and the number of grains (Gn) in relation to the considered parameters of the plants.

show abstract

Section: Resultsmentioning

confidence: 99%

Variation of Some Biometric Parameters in Corn Ears in Relation to Plant Status

KONYA,

HERBEI,

SALA

2023

LSSD

View full text Add to dashboard Cite

show abstract

“…In 2022 Li et al proposed CNN and LSTM-based DL models to predict corn in agroecological regions in China at county level. They used MODIS SR (blue, red, and near-infrared bands), temperature/precipitation data based on the weather stations across China, and China Meteorological Forcing Dataset (CMFD), soil and elevation data [31]. In her Master of Professional Studies (MPS) thesis, Kuang suggested a CNN-GP integrated model for predicting corn yield in 45 counties of U.S. New York state at county level.…”

Section: Literature Surveymentioning

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

“…Recently, image processing technology has been widely applied in agriculture, encompassing crop classification [3,4], pest and disease identification [5,6], and yield estimation [7,8]. Non-contact methods for acquiring plant phenotypic information have become a focal point of interest [9].…”

Section: Introductionmentioning

confidence: 99%

A Method for Calculating the Leaf Area of Pak Choi Based on an Improved Mask R-CNN

Huang,

Li,

Liu

et al. 2024

Agriculture

View full text Add to dashboard Cite

The leaf area of pak choi is a critical indicator of growth rate, nutrient absorption, and photosynthetic efficiency, and it is required to be precisely measured for an optimal agricultural output. Traditional methods often fail to deliver the necessary accuracy and efficiency. We propose a method for calculating the leaf area of pak choi based on an improved Mask R-CNN. We have enhanced Mask R-CNN by integrating an advanced attention mechanism and a two-layer fully convolutional network (FCN) into its segmentation branch. This integration significantly improves the model’s ability to detect and segment leaf edges with increased precision. By extracting the contours of reference objects, the conversion coefficient between the pixel area and the actual area is calculated. Using the mask segmentation output from the model, the area of each leaf is calculated. Experimental results demonstrate that the improved model achieves mean average precision (mAP) scores of 0.9136 and 0.9132 in detection and segmentation tasks, respectively, representing improvements of 1.01% and 1.02% over the original Mask R-CNN. The model demonstrates excellent recognition and segmentation capabilities for pak choi leaves. The error between the calculation result of the segmented leaf area and the actual measured area is less than 4.47%. These results indicate that the proposed method provides a reliable segmentation and prediction performance. It eliminates the need for detached leaf measurements, making it suitable for real-life leaf area measurement scenarios and providing valuable support for automated production technologies in plant factories.

show abstract

Improving maize yield prediction at the county level from 2002 to 2015 in China using a novel deep learning approach

Cited by 19 publications

References 31 publications

Variation of Some Biometric Parameters in Corn Ears in Relation to Plant Status

Variation of Some Biometric Parameters in Corn Ears in Relation to Plant Status

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

A Method for Calculating the Leaf Area of Pak Choi Based on an Improved Mask R-CNN

Contact Info

Product

Resources

About