Recurrent Neural Network-Based Classification of Potato Leaves using RGB Images DOI
Apoorva Sharma,

Avni Sharma

Published: May 2, 2024

In this study, a highly accurate classification system for potato leaves using Recurrent Neural Networks (RNNs) on the Plant Village dataset has been presented. The comprises diverse collection of leaf images, with annotations healthy and those affected by various diseases stressors. Leveraging temporal dependencies inherent in RNNs, it is aimed to effectively capture intricate patterns features sequential data, particularly crucial time-series analysis plant growth stages disease progression. proposed RNN architecture, incorporating long short-term memory (LSTM) units address vanishing gradient problem, demonstrated exceptional performance accurately classifying health, enabling early detection timely interventions improved crop management. Our study demonstrates robustness high accuracy RNNs leaves, metrics exceeding 92%. integration RNN-based systems into precision agriculture holds tremendous promise, providing farmers valuable insights interventions, optimizing ensuring sustainable food production. From experimental outcomes, observed that "RNN Model" records highest 0.927, which higher value compared "CNN (Convolution neural network) (0.902) "Feedforward network" (0.867). success DL model agricultural applications illustrates transformative potential AI technologies addressing global security challenges revolutionizing future agriculture.

Language: Английский

Enhancing Change Detection in Multi-Temporal Optical Images Using a Novel Multi-Scale Deep Learning Approach Based on LSTM DOI
Sahand Tahermanesh, Mehdi Mokhtarzade, Behnam Asghari Beirami

et al.

Advances in Space Research, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 1, 2025

Language: Английский

Citations

1
Land-use and habitat quality prediction in the Fen River Basin based on PLUS and InVEST models DOI Creative Commons

Yanjun Hou,

Juemei Wu

Frontiers in Environmental Science, Journal Year: 2024, Volume and Issue: 12

Published: July 19, 2024

Assessment and prediction analyses of the ecological environmental quality river basins are pivotal to realize protection high-quality coordinated development. Methods: The PLUS InVEST models were used analyze spatiotemporal evolution characteristics land-use in Fen River Basin simulate spatial pattern under natural development (ND), (EC), economic (ED) scenarios 2030, as well evaluate habitat (HQ) its variation from 2000 2030. From 2020, consisted primarily cultivated land, followed by forests, then unused land. Habitat showed a downward trend 2020. Between 2010 rate decline decreased, HQ EC scenario exhibited improvement compared However, there was reduction obvious heterogeneity distribution, showing “low middle high edge”. land converted into construction grasslands, conversion forests dominated changes Basin.

Language: Английский

Citations

4
Introduction to Google Earth Engine: A comprehensive workflow DOI

Nitin Arora,

Sakshi Sakshi,

Sartajvir Singh

et al.

Elsevier eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 3 - 18

Published: Jan. 1, 2025

Language: Английский

Citations

0
AI-driven tools and technologies for agriculture land use & land cover classification using earth observation data analytics DOI
Amandeep Kaur,

Gurwinder Singh,

Sartajvir Singh

et al.

Elsevier eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 527 - 541

Published: Jan. 1, 2025

Language: Английский

Citations

0
A Novel Pixel-based Deep Neural Network in Posterior Probability Space for the Detection of Agriculture Changes Using Remote Sensing Data DOI

Gurwinder Singh,

Narayan Vyas, Neelam Dahiya

et al.

Remote Sensing Applications Society and Environment, Journal Year: 2025, Volume and Issue: unknown, P. 101591 - 101591

Published: May 1, 2025

Language: Английский

Citations

0
Recurrent Neural Network-Based Classification of Potato Leaves using RGB Images DOI
Apoorva Sharma,

Avni Sharma

Published: May 2, 2024

In this study, a highly accurate classification system for potato leaves using Recurrent Neural Networks (RNNs) on the Plant Village dataset has been presented. The comprises diverse collection of leaf images, with annotations healthy and those affected by various diseases stressors. Leveraging temporal dependencies inherent in RNNs, it is aimed to effectively capture intricate patterns features sequential data, particularly crucial time-series analysis plant growth stages disease progression. proposed RNN architecture, incorporating long short-term memory (LSTM) units address vanishing gradient problem, demonstrated exceptional performance accurately classifying health, enabling early detection timely interventions improved crop management. Our study demonstrates robustness high accuracy RNNs leaves, metrics exceeding 92%. integration RNN-based systems into precision agriculture holds tremendous promise, providing farmers valuable insights interventions, optimizing ensuring sustainable food production. From experimental outcomes, observed that "RNN Model" records highest 0.927, which higher value compared "CNN (Convolution neural network) (0.902) "Feedforward network" (0.867). success DL model agricultural applications illustrates transformative potential AI technologies addressing global security challenges revolutionizing future agriculture.

Language: Английский

Citations

0