MFMDLYP: Precision Agriculture through Multidomain Feature Engineering and Multimodal Deep Learning for Enhanced Yield Predictions
Keywords:
Multidomain Feature Engineering, Multimodal Deep Learning, NPK sensing, Precision Agriculture, Yield PredictionAbstract
With the escalating demand for food due to the burgeoning global population, the agricultural sector is under intense pressure to enhance productivity and yield predictability. Precision agriculture emerges as a pivotal approach, enabling real-time, accurate monitoring, and management of agricultural resources, fundamentally transforming smart agriculture scenarios. It leverages advanced technologies to optimize field-level management regarding crop farming. However, the effectiveness of precision agriculture is inherently contingent on the accuracy and timeliness of yield predictions. Current models for yield prediction have exhibited notable limitations, struggling with accuracy, precision, recall, and timeliness in yield predictions. These models predominantly operate on singular data modalities and exhibit a marked deficiency in leveraging multidomain features, which is imperative for holistic soil and crop analysis. The absence of a comprehensive approach integrating various data types like NPK sensor data, image data, and microscopic data limits the depth of analysis and subsequently, the predictive accuracy and precision. The proposed model amalgamates multidomain feature extraction methods, including Frequency, Cosine, Wavelet, and Convolutions, and deploys 1D CNN (Convolutional Neural Network) for NPK data, RNN (Recurrent Neural Network) for image data, and GNN (Graph Neural Network) for microscopic data samples to augment yield prediction efficiency levels. When implemented, the model demonstrates a substantial enhancement in the precision of yield prediction classification by 8.5%, accuracy by 10.4%, recall by 4.5%, and AUC by 2.9%, and concurrently manifests a reduction in the delay of yield prediction by 4.9% compared with existing models. This innovative approach offers a robust, comprehensive solution, enabling precise, timely yield predictions and is advantageous across varied use cases, from optimizing resource allocation to aiding in timely decision-making processes in agricultural practices. The proposed multidomain, multimodal deep learning model significantly advances the domain of precision agriculture. It addresses the prevalent limitations in existing models, offering improved accuracy, precision, and recall, and reducing delays in yield predictions. Its successful implementation across various agricultural scenarios underscores its potential to be a cornerstone in future smart agriculture, aiding in addressing global food security challenges and optimizing agricultural resource management
Downloads
References
Y. Liu, Q. Yu, Q. Zhou, C. Wang, S. D. Bellingrath-Kimura and W. Wu, "Mapping the Complex Crop Rotation Systems in Southern China Considering Cropping Intensity, Crop Diversity, and Their Seasonal Dynamics," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 15, pp. 9584-9598, 2022, doi: 10.1109/JSTARS.2022.3218881.
A. Mateo-Sanchis, J. E. Adsuara, M. Piles, J. Munoz-Marí, A. Perez-Suay and G. Camps-Valls, "Interpretable Long Short-Term Memory Networks for Crop Yield Estimation," in IEEE Geoscience and Remote Sensing Letters, vol. 20, pp. 1-5, 2023, Art no. 2501105, doi: 10.1109/LGRS.2023.3244064.
H. Huang et al., "The Improved Winter Wheat Yield Estimation by Assimilating GLASS LAI Into a Crop Growth Model With the Proposed Bayesian Posterior-Based Ensemble Kalman Filter," in IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1-18, 2023, Art no. 4401818, doi: 10.1109/TGRS.2023.3259742.
F. Ji, J. Meng, Z. Cheng, H. Fang and Y. Wang, "Crop Yield Estimation at Field Scales by Assimilating Time Series of Sentinel-2 Data Into a Modified CASA-WOFOST Coupled Model," in IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1-14, 2022, Art no. 4400914, doi: 10.1109/TGRS.2020.3047102.
A. Reyana, S. Kautish, P. M. S. Karthik, I. A. Al-Baltah, M. B. Jasser and A. W. Mohamed, "Accelerating Crop Yield: Multisensor Data Fusion and Machine Learning for Agriculture Text Classification," in IEEE Access, vol. 11, pp. 20795-20805, 2023, doi: 10.1109/ACCESS.2023.3249205.
X. Li, Y. Dong, Y. Zhu and W. Huang, "Enhanced Leaf Area Index Estimation With CROP-DualGAN Network," in IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1-10, 2023, Art no. 5514610, doi: 10.1109/TGRS.2022.3230354.
Z. Yang, C. Diao and F. Gao, "Towards Scalable Within-Season Crop Mapping With Phenology Normalization and Deep Learning," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 16, pp. 1390-1402, 2023, doi: 10.1109/JSTARS.2023.3237500.
Y. Ma, Z. Yang and Z. Zhang, "Multisource Maximum Predictor Discrepancy for Unsupervised Domain Adaptation on Corn Yield Prediction," in IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1-15, 2023, Art no. 4401315, doi: 10.1109/TGRS.2023.3247343.
Y. Zhang et al., "Enhanced Feature Extraction From Assimilated VTCI and LAI With a Particle Filter for Wheat Yield Estimation Using Cross-Wavelet Transform," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 16, pp. 5115-5127, 2023, doi: 10.1109/JSTARS.2023.3283240.
A. F. Haufler, J. H. Booske and S. C. Hagness, "Microwave Sensing for Estimating Cranberry Crop Yield: A Pilot Study Using Simulated Canopies and Field Measurement Testbeds," in IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1-11, 2022, Art no. 4400411, doi: 10.1109/TGRS.2021.3050171.
B. Yang, J. Guo, J. Liu and X. Ye, "PPCE: A Practical Loss for Crop Mapping Using Phenological Prior," in IEEE Geoscience and Remote Sensing Letters, vol. 20, pp. 1-5, 2023, Art no. 5000605, doi: 10.1109/LGRS.2022.3230421.
N. Farmonov et al., "Crop Type Classification by DESIS Hyperspectral Imagery and Machine Learning Algorithms," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 16, pp. 1576-1588, 2023, doi: 10.1109/JSTARS.2023.3239756.
S. M. M. Nejad, D. Abbasi-Moghadam, A. Sharifi, N. Farmonov, K. Amankulova and M. Lászlź, "Multispectral Crop Yield Prediction Using 3D-Convolutional Neural Networks and Attention Convolutional LSTM Approaches," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 16, pp. 254-266, 2023, doi: 10.1109/JSTARS.2022.3223423.
C. Silva-Perez, A. Marino and I. Cameron, "Learning-Based Tracking of Crop Biophysical Variables and Key Dates Estimation From Fusion of SAR and Optical Data," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 15, pp. 7444-7457, 2022, doi: 10.1109/JSTARS.2022.3203248.
M. R. Khokher et al., "Early Yield Estimation in Viticulture Based on Grapevine Inflorescence Detection and Counting in Videos," in IEEE Access, vol. 11, pp. 37790-37808, 2023, doi: 10.1109/ACCESS.2023.3263238.
M. H. Riaz, H. Imran, H. Alam, M. A. Alam and N. Z. Butt, "Crop-Specific Optimization of Bifacial PV Arrays for Agrivoltaic Food-Energy Production: The Light-Productivity-Factor Approach," in IEEE Journal of Photovoltaics, vol. 12, no. 2, pp. 572-580, March 2022, doi: 10.1109/JPHOTOV.2021.3136158.
H. C. Verma et al., "Development of LR-PCA Based Fusion Approach to Detect the Changes in Mango Fruit Crop by Using Landsat 8 OLI Images," in IEEE Access, vol. 10, pp. 85764-85776, 2022, doi: 10.1109/ACCESS.2022.3194000.
Y. Ma and Z. Zhang, "A Bayesian Domain Adversarial Neural Network for Corn Yield Prediction," in IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1-5, 2022, Art no. 5513705, doi: 10.1109/LGRS.2022.3211444.
Y. Yan et al., "Integration of Canopy Water Removal and Spectral Triangle Index for Improved Estimations of Leaf Nitrogen and Grain Protein Concentrations in Winter Wheat," in IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1-18, 2023, Art no. 4404118, doi: 10.1109/TGRS.2023.3277456.
A. K. Dwivedi, A. K. Singh, D. Singh and H. Kumar, "Development of an Adaptive Linear Mixture Model for Decomposition of Mixed Pixels to Improve Crop Area Estimation Using Artificial Neural Network," in IEEE Access, vol. 11, pp. 5714-5723, 2023, doi: 10.1109/ACCESS.2023.3236665.
S. P. Raja, B. Sawicka, Z. Stamenkovic and G. Mariammal, "Crop Prediction Based on Characteristics of the Agricultural Environment Using Various Feature Selection Techniques and Classifiers," in IEEE Access, vol. 10, pp. 23625-23641, 2022, doi: 10.1109/ACCESS.2022.3154350.
N. Ullah, J. A. Khan, L. A. Alharbi, A. Raza, W. Khan and I. Ahmad, "An Efficient Approach for Crops Pests Recognition and Classification Based on Novel DeepPestNet Deep Learning Model," in IEEE Access, vol. 10, pp. 73019-73032, 2022, doi: 10.1109/ACCESS.2022.3189676.
N. Romero-Puig, J. M. Lopez-Sanchez and M. Busquier, "Evaluation of PolInSAR Observables for Crop-Type Mapping Using Bistatic TanDEM-X Data," in IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1-5, 2022, Art no. 4508005, doi: 10.1109/LGRS.2022.3175689.
M. F. Celik, M. S. Isik, G. Taskin, E. Erten and G. Camps-Valls, "Explainable Artificial Intelligence for Cotton Yield Prediction With Multisource Data," in IEEE Geoscience and Remote Sensing Letters, vol. 20, pp. 1-5, 2023, Art no. 8500905, doi: 10.1109/LGRS.2023.3303643.
M. D. Maas, M. Salvia, P. C. Spennemann and M. E. Fernandez-Long, "Robust Multisensor Prediction of Drought-Induced Yield Anomalies of Soybeans in Argentina," in IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1-4, 2022, Art no. 2504804, doi: 10.1109/LGRS.2022.3171415.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
