Handling Sensor Faults in Hydroponics: A Deep Learning Imputation Technique for Accurate Tomato Yield Prediction

Sensor faults in hydroponic systems pose significant challenges for precision agriculture by compromising the nutrient monitoring accuracy and yield prediction reliability. Current imputation methods lack domain-specific agricultural pattern-preservation capabilities. This paper presents a novel Dee...

Full description

Saved in:
Bibliographic Details
Main Authors: Viji Venugopal, Paresh Tanna, Ramesh Karnati
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10945309/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849699987195166720
author Viji Venugopal
Paresh Tanna
Ramesh Karnati
author_facet Viji Venugopal
Paresh Tanna
Ramesh Karnati
author_sort Viji Venugopal
collection DOAJ
description Sensor faults in hydroponic systems pose significant challenges for precision agriculture by compromising the nutrient monitoring accuracy and yield prediction reliability. Current imputation methods lack domain-specific agricultural pattern-preservation capabilities. This paper presents a novel Deep Learning Precision Imputation Model (DLPIM) based on a generative adversarial network (GAN) architecture to recover missing agricultural data in IoT-based hydroponic monitoring systems. DLPIM introduces a feature encoder-based generator with a 4-headed self-attention mechanism and a Crop Growth Rate (CGR) guided temporal processor to capture complex time-series patterns while maintaining physiological consistency. The discriminator implements dual validity and feature matching pathways, enhanced by minibatch discrimination and spectral normalization. A dataset comprising 1092 data points related to tomato growth and nutrient analysis was utilized to develop and evaluate the proposed model, demonstrating the superior performance of DLPIM compared to nine state-of-the-art imputation methods across different missing data scenarios (10-60%). The proposed model achieved optimal accuracy (MSE =2.367-2.664, MAE =0.795-0.851, R<inline-formula> <tex-math notation="LaTeX">${}^{2} = 0.990$ </tex-math></inline-formula>-0.992), while maintaining consistent performance across all missing rates. Ablation studies confirmed the effectiveness of architectural innovations, with CGR removal resulting in the most substantial performance decline (R<inline-formula> <tex-math notation="LaTeX">${}^{2} = 0.851$ </tex-math></inline-formula> at a 60% missing rate). The DLPIM framework establishes a new benchmark for agricultural time series imputation, enabling robust decision-making in precision agriculture.
format Article
id doaj-art-7e480feeb2cf43cba79877c581247b5b
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-7e480feeb2cf43cba79877c581247b5b2025-08-20T03:18:24ZengIEEEIEEE Access2169-35362025-01-0113657766579610.1109/ACCESS.2025.355587510945309Handling Sensor Faults in Hydroponics: A Deep Learning Imputation Technique for Accurate Tomato Yield PredictionViji Venugopal0https://orcid.org/0000-0002-8004-7583Paresh Tanna1https://orcid.org/0000-0002-0377-0786Ramesh Karnati2Department of Computer Science, RK University of Rajkot, Rajkot, Gujarat, IndiaDepartment of Computer Science, RK University of Rajkot, Rajkot, Gujarat, IndiaDepartment of Computer Science and Engineering, Vardhaman College of Engineering, Hyderabad, IndiaSensor faults in hydroponic systems pose significant challenges for precision agriculture by compromising the nutrient monitoring accuracy and yield prediction reliability. Current imputation methods lack domain-specific agricultural pattern-preservation capabilities. This paper presents a novel Deep Learning Precision Imputation Model (DLPIM) based on a generative adversarial network (GAN) architecture to recover missing agricultural data in IoT-based hydroponic monitoring systems. DLPIM introduces a feature encoder-based generator with a 4-headed self-attention mechanism and a Crop Growth Rate (CGR) guided temporal processor to capture complex time-series patterns while maintaining physiological consistency. The discriminator implements dual validity and feature matching pathways, enhanced by minibatch discrimination and spectral normalization. A dataset comprising 1092 data points related to tomato growth and nutrient analysis was utilized to develop and evaluate the proposed model, demonstrating the superior performance of DLPIM compared to nine state-of-the-art imputation methods across different missing data scenarios (10-60%). The proposed model achieved optimal accuracy (MSE =2.367-2.664, MAE =0.795-0.851, R<inline-formula> <tex-math notation="LaTeX">${}^{2} = 0.990$ </tex-math></inline-formula>-0.992), while maintaining consistent performance across all missing rates. Ablation studies confirmed the effectiveness of architectural innovations, with CGR removal resulting in the most substantial performance decline (R<inline-formula> <tex-math notation="LaTeX">${}^{2} = 0.851$ </tex-math></inline-formula> at a 60% missing rate). The DLPIM framework establishes a new benchmark for agricultural time series imputation, enabling robust decision-making in precision agriculture.https://ieeexplore.ieee.org/document/10945309/Deep learninggenerative AIhydroponicsprecision agriculturesensor system
spellingShingle Viji Venugopal
Paresh Tanna
Ramesh Karnati
Handling Sensor Faults in Hydroponics: A Deep Learning Imputation Technique for Accurate Tomato Yield Prediction
IEEE Access
Deep learning
generative AI
hydroponics
precision agriculture
sensor system
title Handling Sensor Faults in Hydroponics: A Deep Learning Imputation Technique for Accurate Tomato Yield Prediction
title_full Handling Sensor Faults in Hydroponics: A Deep Learning Imputation Technique for Accurate Tomato Yield Prediction
title_fullStr Handling Sensor Faults in Hydroponics: A Deep Learning Imputation Technique for Accurate Tomato Yield Prediction
title_full_unstemmed Handling Sensor Faults in Hydroponics: A Deep Learning Imputation Technique for Accurate Tomato Yield Prediction
title_short Handling Sensor Faults in Hydroponics: A Deep Learning Imputation Technique for Accurate Tomato Yield Prediction
title_sort handling sensor faults in hydroponics a deep learning imputation technique for accurate tomato yield prediction
topic Deep learning
generative AI
hydroponics
precision agriculture
sensor system
url https://ieeexplore.ieee.org/document/10945309/
work_keys_str_mv AT vijivenugopal handlingsensorfaultsinhydroponicsadeeplearningimputationtechniqueforaccuratetomatoyieldprediction
AT pareshtanna handlingsensorfaultsinhydroponicsadeeplearningimputationtechniqueforaccuratetomatoyieldprediction
AT rameshkarnati handlingsensorfaultsinhydroponicsadeeplearningimputationtechniqueforaccuratetomatoyieldprediction