Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Quantum Machine Intelligence

Efficient hybrid quantum-classical neural networks generation for crop yield prediction using sequential satellite images

Sergio Altares-López, Juan José García‐Ripoll, Ángela Ribeiro

Published Nov 11, 2026• 0 citations
PDF (CC BY)Publisher

Abstract

Abstract A novel approach is introduced that enables the automatic generation of hybrid quantum-classical neural networks using a two-step optimization process, combining multiobjective genetic algorithms specifically designed for time series on satellite images with a subsequent continuous refinement stage of the circuit’s parameters. This strategy provides models with low prediction error and low complexity in terms of trainable parameters. The application of this methodology focuses on using Sentinel-2 satellite images to forecast future values of the Normalized Difference Vegetation Index (NDVI), which holds great significance in agriculture since it is used as an indicator of crop health and yield. The hybrid model is evaluated on random validation pixels and full images, and compared against tuned classical baselines to assess its performance.

DOI
10.1007/s42484-026-00468-4

Related papers

Quantum enhanced space based crop yield prediction system for nigerian agriculture: integrating quantum computing with satellite remote sensing

Olakunle Olakunle

Nigerian agriculture employs over 70 percent of rural populations and contributes substantially to national gross domestic product yet confronts mounting challenges from climate variability, resource constraints, and technological inadequacies threatening food security.Current crop yield prediction methodologies demonstrate critical limitations in accuracy, spatial resolution, and processing speed that hamper effective agricultural decision making.Classical computational approaches achieve prediction accuracies rarely exceeding 70 to 80 percent while requiring extended processing times that often render forecasts obsolete for practical farming applications.This research introduces QSCYPS (Quantum Enhanced Space Based Crop Yield Prediction System), integrating quantum computing architectures with satellite remote sensing across Nigerian agro ecological zones.The system employs three quantum algorithms: Quantum Fourier Transform for spectral feature extraction achieving O((log n)²) computational complexity versus classical O(n log n), Quantum Support Vector Machine for crop stress classification reaching 89 percent accuracy in simulation, and Quantum Approximate Optimization Algorithm for parameter calibration of DSSAT crop growth models.Theoretical analysis projects 42 percent reduction in root mean square error from 0.78 tonnes per hectare (classical hybrid baseline) to 0.45 tonnes per hectare for maize predictions, with coefficient of determination improving from 0.86 to 0.94.Computational scaling analysis demonstrates sixteen fold speedup at one million pixel processing scale, with advantages growing at national coverage scales exceeding 280 million pixels.The framework integrates Sentinel 2 imagery at ten metre resolution, ERA5 reanalysis climate data, and ISRIC SoilGrids parameters through Bayesian ensemble combining quantum extracted features with physics based crop models.While projections remain simulation based pending access to actual quantum hardware (IBM 127 qubit Eagle or Google Cirq platforms), QSCYPS establishes theoretical architecture and algorithmic foundation for operational quantum enhanced agricultural intelligence.This represents first integration of quantum information processing with satellite agricultural monitoring, positioning Nigerian institutions at forefront of quantum age precision agriculture.

Journal of Interdisciplinary Postgraduate Research•Mar 18, 2026•0 citations

Quantum machine learning for agricultural remote sensing: Capabilities, applications, and opportunities

Amanjot Bhullar, Nathaniel K. Newlands, R. Ayesha Ali +2 more

Quantum machine learning (QML) is receiving increasing attention as a potential tool for addressing the computational challenges inherent in agricultural remote sensing, where multimodal Earth observational satellite, soil, and climate datasets must be processed at scale. We review recent developments in quantum–classical hybrid modeling for core remote-sensing tasks, including crop type classification, yield estimation, cloud detection, and time series forecasting. Researchers typically combine classical feature extractors with shallow variational circuits or quantum kernels to accommodate the limited qubit counts and noise levels of contemporary quantum devices. We summarize performance trends reported in the literature, emphasizing the role of classical preprocessing, compact quantum circuits, and rigorous benchmarking against strong classical baselines. We consolidate the reviewed studies in a structured comparison covering task, dataset, qubit count, encoding, execution platform, and reported performance relative to classical baselines. The current hardware and data limitations that restrict current QML applications associated with state preparation, circuit depth, and encoding of agricultural datasets are discussed. Near-term prospects for QML in agriculture can involve small-scale hybrid models for multi-class crop mapping and short horizon sequence prediction, while longer-term opportunities may encompass quantum accelerated image segmentation, data fusion, and large scale optimization. Current evidence indicates that QML performance at best matches strong classical baselines, with the most plausible near-term utility arising in narrow settings such as severely label-limited learning and QUBO-structured optimization. Future gains will depend jointly on hardware maturation, data encoding strategies, algorithm design, and integration with classical AI systems.

Computers and Electronics in Agriculture•Sep 7, 2026•0 citations

A Sustainable Quantum-Hybrid Platform for Crop Yield Prediction and Farm Resource Optimization

Sucharita V, Venkateswara Rao P, Srinivasa Rao D

Changes in Weather decrease in soil fertility, limited water resources and growing populations all are making agriculture harder. Even though precision agriculture uses traditional machine learning techniques, the majority of these approaches are unable to effectively handle the extremely complex and multidimensional data coming from crop genetics, weather systems, soil sensors, and satellite surveillance. In this regard, the current research presents a framework for intelligent agriculture that is based on quantum machine learning and quantum optimization. The system can represent and analyze the agricultural data far more efficiently than traditional computer methods by taking advantage of quantum phenomena like superposition and entanglement. Improved crop yield prediction and intelligent resource management via quantum-inspired optimization, particularly QAOA, are the two main objectives of the work. The model achieves accuracy values for yield estimates between 70 and 90%, according to simulation results, and it allows for real-time modification of fertilizer and irrigation. Lastly, it provides farmers with an easy-to-use dashboard to visualize insights. The current study provides a conceptual and technical foundation for quantum computing applications in agriculture in the near future, for more resource-efficient, data-driven, and sustainable farming, even though current quantum hardware is still in the development stage.

•Mar 28, 2026•0 citations

Design and Development of Image based Climate Prediction Model by using Quantum Computing Technology

Sandhya K. Yerra, Vivek Pandey, Sunita D. Singh +3 more

Climate prediction plays a crucial role in understanding and mitigating the impacts of climate change. Traditional climate models, though powerful, often face challenges in handling the vast, high-dimensional satellite imagery data required for accurate forecasting. Meanwhile, quantum computing offers new computational paradigms capable of addressing complex problems intractable for classical systems. In this research, we propose an innovative framework for an image-based climate prediction model leveraging quantum computing technology. By integrating quantum machine learning algorithms with satellite Earth observation data, the model aims to extract critical climatic patterns such as temperature anomalies, cloud movements, and vegetation dynamics with enhanced precision and computational efficiency. The study addresses existing limitations by developing specialized quantum algorithms for image processing, exploring quantum-classical hybrid architectures, and optimizing the system for real-world scalability using current and near-term quantum devices. Preliminary results suggest that quantum approaches have the potential to outperform traditional techniques in processing speed and predictive accuracy, particularly for high-resolution, time-series satellite imagery. This work represents a significant step toward practical, quantum-enhanced climate modeling, bridging the gap between quantum computing advancements and urgent global climate forecasting needs.

IEEE International Conference on Advances in Computing Research on Science Engineering and Technology (ACROSET)•Sep 27, 2025•3 citations

Quantum and quantum-inspired neural networks for time series forecasting: A systematic review with agricultural applications

Sujith Arokia Swamy B, Raj Shekar M, Bhavana Kabber +1 more

Quantum machine learning (QML) has emerged as a promising paradigm for time series forecasting, offering potential advantages in expressivity, parameter efficiency, and computational scaling through quantum mechanical principles such as superposition, entanglement, and interference. This systematic review synthesizes 112 primary studies published between 2020 and 2026, providing the first comprehensive assessment of quantum and quantum-inspired neural networks for time series forecasting with a dedicated focus on agricultural applications. We develop a taxonomy distinguishing fully quantum models (Quantum RNNs, Quantum LSTMs), hybrid quantum-classical architectures (QLSTM, Q-Informer, QKAN-LSTM), quantum kernel methods (QSVM, QK-LSTM), quantum reservoir computing (QRC), and quantum-inspired classical algorithms. Our synthesis finds that (i) Quantum LSTM (QLSTM) models consistently outperform classical LSTM baselines across weather, financial, and climate forecasting tasks; (ii) Quantum Reservoir Computing achieves competitive accuracy with significantly fewer trainable parameters, making it particularly suited to data-scarce agricultural price forecasting; (iii) hybrid quantum-classical frameworks for rice yield prediction achieve near-perfect accuracy (R2 = 0.99992); (iv) QKAN-LSTM achieves a 79% reduction in trainable parameters; (v) Q-Informer introduces learnable quantum attention scoring; and (vi) QRC applied to food price crisis prediction outperforms deep learning and statistical baselines. Despite these advances, we identify seven critical gaps: absence of standardized quantum benchmarking, hardware scalability limitations, noise resilience challenges, lack of reproducibility, limited cross-commodity validation, interpretability barriers, and the simulation-reality gap.

International Journal of Agriculture Extension and Social Development•Mar 1, 2026•0 citations

Quantum Machine Learning for Crop Disease Prediction and Forecasting

Jhenkar N, Mallikarjun TD, Madhuri V +2 more

Accurate and timely identification of crop diseases is critical for ensuring agricultural productivity. This work presents a hybrid quantum - classical machine learning framework for early detection of tomato crop diseases—specifically Early Blight, Late Blight, and Tomato Mosaic Virus (TMV). Data was collected using an ESP32-S3-based sensor kit measuring environmental and plant health parameters. Ground truth labeling was validated through a custom-trained convolutional neural networks (CNN) leaf image classifier, aligning disease symptoms with real-time sensor data.Extensive experiments comparing classical machine learning models with three hybrid Quantum Machine Learning (QML) models revealed notable improvements. The QML-Decision Tree hybrid significantly reduced overfitting from 6.36% to 0.68%, while improving generalization with a 15–18% increase in F1-score over classical counterparts. Similarly, the QML-Random Forest model lowered the overfitting margin from 4.68% to 3.79%, demonstrating better consistency on unseen data. The MobileNetV2 model used for image-based classification achieved 94.6% accuracy, outperforming conventional CNN models.A Raspberry Pi 4-based autonomous field rover was then developed, integrating the CNN model for real-time disease detection. An AI assistant is also incorporated into the prototype system to give farmers illness insights. When a condition is identified, a QR code is used to provide a treatment card that includes information on symptoms, preventative measures, and carefully chosen therapy links. A forecasting module was developed to use current sensor data to anticipate disease risks over a period of 4–7 days in order to facilitate prior action. The groundwork of intelligent, scalable, and quantum-assisted precision farming is laid by this work.

IEEE International Conference on Cybernetics, Cognition and Machine Learning Applications (ICCCMLA)•Nov 1, 2025•0 citations
Abstract A novel approach is introduced that enables the automatic generation of hybrid quantum-classical neural networks using a two-step optimization process, combining multiobjective genetic algorithms specifically designed for time series on satellite images with a subsequent continuous refinement stage of the circuit’s parameters. This strategy provides models with low prediction error and low complexity in terms of trainable parameters. The application of this methodology focuses on using Sentinel-2 satellite images to forecast future values of the Normalized Difference Vegetation Index (NDVI), which holds great significance in agriculture since it is used as an indicator of crop health and yield. The hybrid model is evaluated on random validation pixels and full images, and compared against tuned classical baselines to assess its performance.
Nigerian agriculture employs over 70 percent of rural populations and contributes substantially to national gross domestic product yet confronts mounting challenges from climate variability, resource constraints, and technological inadequacies threatening food security.Current crop yield prediction methodologies demonstrate critical limitations in accuracy, spatial resolution, and processing speed that hamper effective agricultural decision making.Classical computational approaches achieve prediction accuracies rarely exceeding 70 to 80 percent while requiring extended processing times that often render forecasts obsolete for practical farming applications.This research introduces QSCYPS (Quantum Enhanced Space Based Crop Yield Prediction System), integrating quantum computing architectures with satellite remote sensing across Nigerian agro ecological zones.The system employs three quantum algorithms: Quantum Fourier Transform for spectral feature extraction achieving O((log n)²) computational complexity versus classical O(n log n), Quantum Support Vector Machine for crop stress classification reaching 89 percent accuracy in simulation, and Quantum Approximate Optimization Algorithm for parameter calibration of DSSAT crop growth models.Theoretical analysis projects 42 percent reduction in root mean square error from 0.78 tonnes per hectare (classical hybrid baseline) to 0.45 tonnes per hectare for maize predictions, with coefficient of determination improving from 0.86 to 0.94.Computational scaling analysis demonstrates sixteen fold speedup at one million pixel processing scale, with advantages growing at national coverage scales exceeding 280 million pixels.The framework integrates Sentinel 2 imagery at ten metre resolution, ERA5 reanalysis climate data, and ISRIC SoilGrids parameters through Bayesian ensemble combining quantum extracted features with physics based crop models.While projections remain simulation based pending access to actual quantum hardware (IBM 127 qubit Eagle or Google Cirq platforms), QSCYPS establishes theoretical architecture and algorithmic foundation for operational quantum enhanced agricultural intelligence.This represents first integration of quantum information processing with satellite agricultural monitoring, positioning Nigerian institutions at forefront of quantum age precision agriculture.
Quantum machine learning (QML) is receiving increasing attention as a potential tool for addressing the computational challenges inherent in agricultural remote sensing, where multimodal Earth observational satellite, soil, and climate datasets must be processed at scale. We review recent developments in quantum–classical hybrid modeling for core remote-sensing tasks, including crop type classification, yield estimation, cloud detection, and time series forecasting. Researchers typically combine classical feature extractors with shallow variational circuits or quantum kernels to accommodate the limited qubit counts and noise levels of contemporary quantum devices. We summarize performance trends reported in the literature, emphasizing the role of classical preprocessing, compact quantum circuits, and rigorous benchmarking against strong classical baselines. We consolidate the reviewed studies in a structured comparison covering task, dataset, qubit count, encoding, execution platform, and reported performance relative to classical baselines. The current hardware and data limitations that restrict current QML applications associated with state preparation, circuit depth, and encoding of agricultural datasets are discussed. Near-term prospects for QML in agriculture can involve small-scale hybrid models for multi-class crop mapping and short horizon sequence prediction, while longer-term opportunities may encompass quantum accelerated image segmentation, data fusion, and large scale optimization. Current evidence indicates that QML performance at best matches strong classical baselines, with the most plausible near-term utility arising in narrow settings such as severely label-limited learning and QUBO-structured optimization. Future gains will depend jointly on hardware maturation, data encoding strategies, algorithm design, and integration with classical AI systems.
Changes in Weather decrease in soil fertility, limited water resources and growing populations all are making agriculture harder. Even though precision agriculture uses traditional machine learning techniques, the majority of these approaches are unable to effectively handle the extremely complex and multidimensional data coming from crop genetics, weather systems, soil sensors, and satellite surveillance. In this regard, the current research presents a framework for intelligent agriculture that is based on quantum machine learning and quantum optimization. The system can represent and analyze the agricultural data far more efficiently than traditional computer methods by taking advantage of quantum phenomena like superposition and entanglement. Improved crop yield prediction and intelligent resource management via quantum-inspired optimization, particularly QAOA, are the two main objectives of the work. The model achieves accuracy values for yield estimates between 70 and 90%, according to simulation results, and it allows for real-time modification of fertilizer and irrigation. Lastly, it provides farmers with an easy-to-use dashboard to visualize insights. The current study provides a conceptual and technical foundation for quantum computing applications in agriculture in the near future, for more resource-efficient, data-driven, and sustainable farming, even though current quantum hardware is still in the development stage.
Climate prediction plays a crucial role in understanding and mitigating the impacts of climate change. Traditional climate models, though powerful, often face challenges in handling the vast, high-dimensional satellite imagery data required for accurate forecasting. Meanwhile, quantum computing offers new computational paradigms capable of addressing complex problems intractable for classical systems. In this research, we propose an innovative framework for an image-based climate prediction model leveraging quantum computing technology. By integrating quantum machine learning algorithms with satellite Earth observation data, the model aims to extract critical climatic patterns such as temperature anomalies, cloud movements, and vegetation dynamics with enhanced precision and computational efficiency. The study addresses existing limitations by developing specialized quantum algorithms for image processing, exploring quantum-classical hybrid architectures, and optimizing the system for real-world scalability using current and near-term quantum devices. Preliminary results suggest that quantum approaches have the potential to outperform traditional techniques in processing speed and predictive accuracy, particularly for high-resolution, time-series satellite imagery. This work represents a significant step toward practical, quantum-enhanced climate modeling, bridging the gap between quantum computing advancements and urgent global climate forecasting needs.
Quantum machine learning (QML) has emerged as a promising paradigm for time series forecasting, offering potential advantages in expressivity, parameter efficiency, and computational scaling through quantum mechanical principles such as superposition, entanglement, and interference. This systematic review synthesizes 112 primary studies published between 2020 and 2026, providing the first comprehensive assessment of quantum and quantum-inspired neural networks for time series forecasting with a dedicated focus on agricultural applications. We develop a taxonomy distinguishing fully quantum models (Quantum RNNs, Quantum LSTMs), hybrid quantum-classical architectures (QLSTM, Q-Informer, QKAN-LSTM), quantum kernel methods (QSVM, QK-LSTM), quantum reservoir computing (QRC), and quantum-inspired classical algorithms. Our synthesis finds that (i) Quantum LSTM (QLSTM) models consistently outperform classical LSTM baselines across weather, financial, and climate forecasting tasks; (ii) Quantum Reservoir Computing achieves competitive accuracy with significantly fewer trainable parameters, making it particularly suited to data-scarce agricultural price forecasting; (iii) hybrid quantum-classical frameworks for rice yield prediction achieve near-perfect accuracy (R2 = 0.99992); (iv) QKAN-LSTM achieves a 79% reduction in trainable parameters; (v) Q-Informer introduces learnable quantum attention scoring; and (vi) QRC applied to food price crisis prediction outperforms deep learning and statistical baselines. Despite these advances, we identify seven critical gaps: absence of standardized quantum benchmarking, hardware scalability limitations, noise resilience challenges, lack of reproducibility, limited cross-commodity validation, interpretability barriers, and the simulation-reality gap.
Accurate and timely identification of crop diseases is critical for ensuring agricultural productivity. This work presents a hybrid quantum - classical machine learning framework for early detection of tomato crop diseases—specifically Early Blight, Late Blight, and Tomato Mosaic Virus (TMV). Data was collected using an ESP32-S3-based sensor kit measuring environmental and plant health parameters. Ground truth labeling was validated through a custom-trained convolutional neural networks (CNN) leaf image classifier, aligning disease symptoms with real-time sensor data.Extensive experiments comparing classical machine learning models with three hybrid Quantum Machine Learning (QML) models revealed notable improvements. The QML-Decision Tree hybrid significantly reduced overfitting from 6.36% to 0.68%, while improving generalization with a 15–18% increase in F1-score over classical counterparts. Similarly, the QML-Random Forest model lowered the overfitting margin from 4.68% to 3.79%, demonstrating better consistency on unseen data. The MobileNetV2 model used for image-based classification achieved 94.6% accuracy, outperforming conventional CNN models.A Raspberry Pi 4-based autonomous field rover was then developed, integrating the CNN model for real-time disease detection. An AI assistant is also incorporated into the prototype system to give farmers illness insights. When a condition is identified, a QR code is used to provide a treatment card that includes information on symptoms, preventative measures, and carefully chosen therapy links. A forecasting module was developed to use current sensor data to anticipate disease risks over a period of 4–7 days in order to facilitate prior action. The groundwork of intelligent, scalable, and quantum-assisted precision farming is laid by this work.