A Genetic Algorithm-Based Soil Fertilizer Recommendation System: Real-Valued Optimization Grounded in Liebig’s Law of the Minimum
Release :
2026/09/11
Language :
en
Year :
2026
Issue :
Vol. 1 / Issue 1
Pages :
18-24
Download Count
72
Authors:
Abstract:
Agricultural sustainability underpins global food security, yet optimizing fertilizer application remains a critical challenge. Under-application leads to yield loss, while over-application causes environmental pollution and economic waste. This study presents a Genetic Algorithm (GA)-based optimization framework that recommends a fertilizer blend for individual soil samples. Taking nitrogen (N), phosphorus (P), and potassium type crop variety as input, the system searches a seven-dimensional dosage space (kg/ha) spanning seven commercial fertilizers. The fitness function is grounded in Liebig’s Law of the Minimum, augmented with total-cost and nutrient-overshoot penalties to yield a multi-objective structure. The GA comprises BLX-α crossover, Gaussian mutation, tournament selection, and elitism operators. The system is validated on a dataset of 8,000 field records spanning eleven crop types and five soil categories. Case studies conducted on five representative crops demonstrate consistent convergence within 120 generations. In a batch analysis of 500 samples, the distribution of GA recommendations aligns with agronomic nutrient-deficiency patterns rather than with historical labels.
Download Full Article (PDF)
Complete research paper with figures, tables, and references
1Alvarez, R., 2009 Predicting average regional yield and production of wheat by an artificial neural network approach. European Journal of Agronomy 30: 70–77.
2Brady, N. C. and R. R. Weil, 2008 The Nature and Properties of Soils. Pearson Education, Upper Saddle River, NJ, 14th edition.
3Dahikar, S. S. and S. V. Rode, 2014 Agricultural crop selection and recommendation using data mining. International Journal of Innovative Science and Modern Engineering 2: 54–57.
4Dimopoulos, C., A. M. S. Zalzala, and Z. Shahab, 2007 Genetic algorithm optimization for crop rotation planning. Applied Soft Computing 7: 977–987.
5Eshelman, L. J. and J. D. Schaffer, 1993 Real-coded genetic algorithms and interval schemata. Foundations of Genetic Algorithms 2: 187–202.
6Food and Agriculture Organization of the United Nations, 2021 The state of food and agriculture 2021. Technical report, FAO, Roma.
7Goldberg, D. E., 1989 Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley, Reading, MA.
8Guo, Y. et al., 2022 Deep learning for visual understanding: A review. Neurocomputing 187: 27–48.
9Holland, J. H., 1992 Adaptation in Natural and Artificial Systems. MIT Press, Cambridge, MA, second edition.
10Janssen, B. H. et al., 1990 A system for quantitative evaluation of the fertility of tropical soils (quefts). Geoderma 46: 299–318.
11Jin, Y., 2011 Surrogate-assisted evolutionary computation: Recent advances and future challenges. Swarm and Evolutionary Computation 1: 61–70.
12McClendon, R. W. and G. Hoogenboom, 2002 A crop yield neural network model for precision farming. Agricultural Systems 74: 553–572.
13Mishra, A., N. Jain, and A. Shukla, 2021 Machine learning-based crop recommendation system. Journal of Ambient Intelligence and Humanized Computing 12: 7151–7164.
14Pal, M. and V. Mahajan, 2019 Genetic algorithm based npk ratio optimization for crop production. International Journal of Computer Applications 178: 1–5.
15Tilman, D., K. G. Cassman, P. A. Matson, R. Naylor, and S. Polasky, 2002 Agricultural sustainability and intensive production practices. Nature 418: 671–677.
16Umamahesh, N. V. and P. Sreenivasulu, 2003 Genetic algorithm for optimal irrigation scheduling. Irrigation and Drainage 52: 123–133.
17von Liebig, J., 1840 Organic Chemistry in Its Application to Agriculture and Physiology. Taylor and Walton, Londra.
18Wang, J., L. Zhang, and H. Chen, 2023 Deep neural networks for multi-output fertilizer dosage regression. Computers and Electronics in Agriculture 205: 107589.