Improved data clustering methods and integrated A-FP algorithm for crop yield prediction

Vani, Pranali; Rathi, Sheetal

doi:10.1007/s10619-021-07350-1

Cited by 5 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Vani and Rathi 29 initially used a logical linear regression model for preprocessing the collected agricultural data. Next, the expected likelihood maximization (ELM) and proximity Manhattan distance estimation (PMDE) were applied to densely and sparsely distribute the data.…”

Section: Related Workmentioning

confidence: 99%

Crop yield forecasting by long short‐term memory network with Adam optimizer and Huber loss function in Andhra Pradesh, India

Dwaram

Madapuri

2022

Concurrency and Computation

View full text Add to dashboard Cite

Summary In recent times, crop yield prediction gains more attention among researchers communities to expand food production. In this article, an effort is done for crop yield prediction in Andhra Pradesh state (India), because AP highly contributes to the Indian economy. Especially, the crop yield prediction is done for Western Godavari, Prakasam, Guntur, Srikakulam, Krishna, Vizianagaram, Visakhapatnam, and Nellore districts of Andhra Pradesh (India) by estimating the rainfall based on the attributes: average temperature, minimum temperature, maximum temperature, precipitation, cloud cover, and velocity potential. After collecting the data from the Telangana agricultural report (2017–2018), the collected data are preprocessed utilizing the min‐max normalization technique, which is effective in preserving the relationship among data. The normalized data are classified using long short term memory network with Adam optimizer and Huber loss function. The proposed classifier has adaptive learning rates for dissimilar parameters by identifying the first and second‐moment gradient estimation so it has better computational effectiveness, unlike other classifiers. The proposed classifier predicts each site in the collected dataset into one of the three crops: rice, sugarcane, and onion. Finally, the agriculture experts validate the obtained results of the proposed model.

show abstract

Section: Related Workmentioning

confidence: 99%