A Hybrid RF-Attentive BiLSTM Framework for the Agroclimatic Mapping of Arecanut Yield in Central Karnataka

S. Sushitha; K. Aparna

doi:10.48084/etasr.18172

Authors

S. Sushitha BMS Institute of Technology and Management, Bangalore, Visvesvaraya Technological University, Belagavi, India
K. Aparna BMS Institute of Technology and Management, Bangalore, Visvesvaraya Technological University, Belagavi, India

Volume: 16 | Issue: 3 | Pages: 34957-34964 | June 2026 | https://doi.org/10.48084/etasr.18172

Received: 14 February 2026 | Revised: 18 March 2026 | Accepted: 26 March 2026 | Online: 6 June 2026

Corresponding author: S. Sushitha

Abstract

Climate variability, geographical disparity, and the lack of agricultural datasets make it difficult to estimate Arecanut crop production in Central Karnataka. Existing machine learning and deep learning models often fail to capture nonlinear climatic interactions as well as temporal climate dynamics. To address this, this research proposes a novel hybrid Random Forest (RF)–attentive Bidirectional Long Short-Term Memory (BiLSTM) framework for the agroclimatic mapping of the Arecanut crop. To handle the class imbalance problem and to enhance feature representation, the Synthetic Minority Over-sampling Technique combined with Edited Nearest Neighbors (SMOTE-ENN) resampling technique is employed in the present study. Here, the RF module extracts nonlinear climatic interactions, whereas the attentive BiLSTM module captures temporal climate patterns that strongly influence the Arecanut growth cycle. The use of a self-attention model helps improve the dynamic weighting of historical observations, whereas the BiLSTM model learns relevant features, improving overall performance. The effectiveness of the developed model is evaluated through comparative analysis with other state-of-the-art solutions. The hybrid model outperforms all baseline models, achieving the highest coefficient of determination (R² = 0.914), the lowest Root Mean Square Error (RMSE = 0.39), the lowest Mean Absolute Error (MAE = 0.30), and the lowest Mean Absolute Percentage Error (MAPE = 8.1%). The high correlation coefficient (r = 0.956) further demonstrates the strong predictive capability of the model in capturing crop–climate interactions and confirms the superiority of the proposed hybrid model in agroclimatic mapping.

Keywords:

Arecanut yield prediction, Random Forest (RF), BiLSTM feature learning, climate analysis, Arecanut yield, precision agriculture

References

T. F. Fotabong et al., "Soil Analysis Using Deep Learning for Precision Agriculture," in 2024 First International Conference on Pioneering Developments in Computer Science & Digital Technologies, Delhi, India, 2024, pp. 303–307.

S. K. Phang, T. H. A. Chiang, A. Happonen, and M. M. L. Chang, "From Satellite to UAV-Based Remote Sensing: A Review on Precision Agriculture," IEEE Access, vol. 11, pp. 127057–127076, 2023.

FAO, "The future of food and agriculture: trends and challenges," Food and Agriculture Organization of the United Nations, Rome, 2017.

M. R. Evans, D. Oliver, X. Zhou, and S. Shekhar, "Spatial Big Data: Case Studies on Volume, Velocity, and Variety," in Big Data, 2nd ed., H. A. Karimi, Ed. Boca Raton, FL, USA: CRC Press, 2024, ch. 8.

P. Helber, B. Bischke, C. Packbier, P. Habelitz, and F. Seefeldt, "An Operational Approach to Large-Scale Crop Yield Prediction with Spatio-Temporal Machine Learning Models," in IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, Athens, Greece, 2024, pp. 4299–4302.

M. J. Wellington, R. Lawes, and P. Kuhnert, "A framework for modelling spatio-temporal trends in crop production using generalised additive models," Computers and Electronics in Agriculture, vol. 212, Sept. 2023, Art. no. 108111.

B. S. Sidhu, Z. Mehrabi, N. Ramankutty, and M. Kandlikar, "How can machine learning help in understanding the impact of climate change on crop yields?," Environmental Research Letters, vol. 18, no. 2, Jan. 2023, Art. no. 024008.

L. Wickramasinghe, R. Weliwatta, P. Ekanayake, and J. Jayasinghe, "Modeling the Relationship between Rice Yield and Climate Variables Using Statistical and Machine Learning Techniques," Journal of Mathematics, vol. 2021, no. 1, Feb. 2021, Art. no. 6646126.

B. N. S. GUPTA and U. Lekhana, "Crop Recommender System Using Machine Learning Approach," International Journal of Engineering Research and Science & Technology, vol. 20, no. 2, pp. 1167–1177, June 2024.

V. H. Kalmani, N. V. Dharwadkar, and V. Thapa, "Crop Yield Prediction using Deep Learning Algorithm based on CNN-LSTM with Attention Layer and Skip Connection," Indian Journal Of Agricultural Research, vol. 59, no. 8, pp. 1303–1311, Nov. 2025.

S. M. V, J. P, G. George, P. S, and K. N, "Hybrid Deep Learning Models for Precision and Sustainable Crop Management," in 2025 IEEE 6th Global Conference for Advancement in Technology, Bangalore, India, 2025, pp. 1–7.

H. He and E. A. Garcia, "Learning from Imbalanced Data," IEEE Transactions on Knowledge and Data Engineering, vol. 21, no. 9, pp. 1263–1284, Sept. 2009.

N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, "SMOTE: Synthetic Minority Over-sampling Technique," Journal of Artificial Intelligence Research, vol. 16, pp. 321–357, June 2002.

D. L. Wilson, "Asymptotic Properties of Nearest Neighbor Rules Using Edited Data," IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-2, no. 3, pp. 408–421, July 1972.

H. B P, A. K. K M, S. S, and A. K, "Karnataka's Arecanut Boom: Understanding the Current Scenario and Factors Driving the Shift," vol. 6, no. 8, Krishi Science – eMagazine for Agricultural Sciences, pp. 1–6, Aug. 06, 2025.

P. K, S. H.L., K. Sharma, and M. S. Nayak, "Cultivating arecanut in India: challenges, opportunities and sustainable practices," Madras Agricultural Journal, vol. 111, no. 4, pp. 58–70, Dec. 2024.

R. Bhat, S. Sujatha, Bhavishya, U. K. Priya, A. Gupta, and A. Uchoi, "Arecanut (Areca catechu L.)," in Soil Health Management for Plantation Crops: Recent Advances and New Paradigms, G. V. Thomas and V. Krishnakumar, Eds. Singapore: Springer Nature, 2024, pp. 177–206.

K. M. Sunil, V. S. Devadas, and S. P. George, "Influence of Weather Parameters on Yield and Yield Attributes of Areca Nut (Areca catechu L.)," Journal of Agricultural Physics, vol. 11, pp. 88–90, 2011.

S. Sujatha, R. Bhat, and S. E. Apshara, "Climate change, weather variability and associated impact on arecanut and cocoa in humid tropics of India," International Journal of Innovative Horticulture, vol. 7, no. 1, pp. 27–37, 2018.

K. B. Hebbar, A. S. P, S. Jose V, R. S v, and R. Bhat, "Predicting current and future climate suitability for arecanut (Areca catechu L.) in India using ensemble model," Heliyon, vol. 10, no. 4, Feb. 2024, Art. no. e26382.

C. T. Jose, K. P. Chandran, K. Muralidharan, and S. Jayasekhar, "Crop weather relationship in arecanut," Journal of Plantation Crops, vol. 47, no. 3, pp. 145–151, 2019.

J. H. Jeong et al., "Random Forests for Global and Regional Crop Yield Predictions," Plos One, vol. 11, no. 6, June 2016, Art. no. e0156571.

Z. K. Jabal, T. S. Khayyun, and I. A. Alwan, "Impact of Climate Change on Crops Productivity Using MODIS-NDVI Time Series," Civil Engineering Journal, vol. 8, no. 6, pp. 1136–1156, June 2022.

D. B. Lobell, D. Thau, C. Seifert, E. Engle, and B. Little, "A scalable satellite-based crop yield mapper," Remote Sensing of Environment, vol. 164, pp. 324–333, July 2015.

R. P. P. Guthu and S. R. Bellipady, "A Formal Statistical Data Modeling for Knowledge Discovery and Prognostic Reasoning of Arecanut Crop using Data Analytics," International Journal of Software Science and Computational Intelligence, vol. 14, no. 1, pp. 1–27, 2022.

R. Krishna, P. K. V, and R. Gaonkar, "Areca Nut Disease Dataset Creation and Validation using Machine Learning Techniques based on Weather Parameters," Engineered Science, vol. 19, no. 4, pp. 205–214, June 2022.

P. B. R and N. P. S, "A Literature Review of the Detection and Categorization of various Arecanut Diseases using Image Processing and Machine Learning Approaches," International Journal of Applied Engineering and Management Letters, vol. 5, no. 2, pp. 183–204, Dec. 2021.

K. A. Garrett et al., "Complexity in climate-change impacts: an analytical framework for effects mediated by plant disease," Plant Pathology, vol. 60, no. 1, pp. 15–30, 2011.

B. Patil et al., "Exploring the Impact of Climatic Variables on Arecanut Fruit Rot Epidemic by Understanding the Disease Dynamics in Relation to Space and Time," Journal of Fungi, vol. 8, no. 7, July 2022, Art. no. 745.

K. Rajashree, K. V. Prema, G. Rajath, and S. Angad, "Prediction of fruit rot disease incidence in Arecanut based on weather parameters," vol. 22, no. S1, pp. 1117–1133, Nov. 2022.

A. B. Tejaswini, H. S. Padmashri, D. V. Soumya, T. N. Prakash Kammardi, and H. G. Hemalatha, "Association studies of climate factors on arecanut yield in Western Ghats region Karnataka.," Environment & Ecology, vol. 32, no. 3A, pp. 1085–1087, July 2014.

S. Jayasekhar, C. T. Jose, C. Thamban, and K. Muralidharan, "Economic impact of arecanut based cropping systems: A study of Dakshina Kannada district-Karnataka," Journal of Plantation Crops, vol. 40, no. 1, pp. 50–55, June 2012.

P. K, G. Naik, M. K. Naik, V. Hegde, B. C. Dhananjaya, and S. M. K., "Exploring Yellow Leaf Disease Patterns in Areca Plantations in Chikkamagaluru District of Karnataka," Saudi Journal of Pathology and Microbiology, vol. 9, no. 3, pp. 63–70, Mar. 2024.

J. You, X. Li, M. Low, D. Lobell, and S. Ermon, "Deep Gaussian Process for Crop Yield Prediction Based on Remote Sensing Data," Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31, no. 1, pp. 4559–4565, Feb. 2017.

"Area, Production and Yield (APY) Statistics Portal." Directorate of Economics and Statistics, Department of Agriculture and Farmer Welfare, Government of India. https://data.desagri.gov.in/website/apy-query-report-web.

"Data Access Viewer (DAV)." Nasa Power. https://power.larc.nasa.gov/data-access-viewer/.

"QGIS Geographic Information System." Open-Source Geospatial Foundation Project. https://qgis.org/.

N. G. Renukaradya and K. G. Rao, "A Long Short-Term Memory Guided Conditional Dynamic Variational Auto-Encoder for Crop Yield Prediction and Crop Type Classification," Engineering, Technology & Applied Science Research, vol. 15, no. 6, pp. 29770–29778, Dec. 2025.