Classification of soil types based on suitable plants using Multiclass Classification Artificial Neural Network

Ivan Budianto, Nova El Maidah, Saiful Bukhori

Abstract


Soil conditions are one of the factors that determine plant growth. For plants, soil is a place for plant growth, a place for air supply, a place for nutrient supply, and a place for plant growth. Soil conditions are divided into two, namely chemically and physically. Chemical soil conditions include the content of Sodium, Phosphorus, Hydrogen, Potassium and Calcium. Meanwhile, physically it includes daily temperature, humidity, pH, and rainfall. This research develops a neural network model to recognize soil condition data patterns with predetermined parameters. The parameters used in this research were the chemical conditions of the soil, namely levels of Nitrogen, Phosphorus and Potassium, as well as the physical condition of the soil which included temperature, humidity, pH and rainfall. After identifying the soil condition data pattern, it is used to classify soil types based on the appropriate plants. This research develops a model with 9 scenarios that vary in the ratio of data splitting and the number of layers used. Based on all trials conducted, the best scenario is the splitting of 90% training data, 5% validation data, and 5% test data with 4 layers. This model has a training accuracy of 99.30%, a validation accuracy of 99.24%, and a test accuracy of 98.93%. Model testing in this scenario is also the best with 99.24% precision, 99.49% recall, and 99.32% F1 score.

Full Text:

PDF

References


B. Keulemans, W., Bylemans, D., De Coninck, Farming without plant protection products: Can we grow without using herbicides, fungicides and insecticides?, no. March. 2019.

B. S. Adeleke and O. O. Babalola, “Oilseed crop sunflower (Helianthus annuus) as a source of food: Nutritional and health benefits,” Food Sci. Nutr., vol. 8, no. 9, pp. 4666–4684, 2020, doi: 10.1002/fsn3.1783.

D. Serebrennikov, F. Thorne, Z. Kallas, and S. N. McCarthy, “Factors influencing adoption of sustainable farming practices in europe: A systemic review of empirical literature,” Sustain., vol. 12, no. 22, pp. 1–23, 2020, doi: 10.3390/su12229719.

H. Mehbub et al., “Tissue Culture in Ornamentals: Cultivation Factors, Propagation Techniques, and Its Application,” Plants, vol. 11, no. 23, 2022, doi: 10.3390/plants11233208.

H. Upadhyay et al., “Exploration of Crucial Factors Involved in Plants Development Using the Fuzzy AHP Method,” Math. Probl. Eng., vol. 2022, 2022, doi: 10.1155/2022/4279694.

M. F. Seleiman et al., “Drought stress impacts on plants and different approaches to alleviate its adverse effects,” Plants, vol. 10, no. 2, pp. 1–25, 2021, doi: 10.3390/plants10020259.

A. Tataridas, P. Kanatas, A. Chatzigeorgiou, S. Zannopoulos, and I. Travlos, “Sustainable Crop and Weed Management in the Era of the EU Green Deal: A Survival Guide,” Agronomy, vol. 12, no. 3, pp. 1–23, 2022, doi: 10.3390/agronomy12030589.

A. Javed, E. Ali, K. Binte Afzal, A. Osman, and D. S. Riaz, “Soil Fertility: Factors Affecting Soil Fertility, and Biodiversity Responsible for Soil Fertility,” Int. J. Plant, Anim. Environ. Sci., vol. 12, no. 01, pp. 21–33, 2022, doi: 10.26502/ijpaes.202129.

N. M. Alzamel, E. M. M. Taha, A. A. A. Bakr, and N. Loutfy, “Effect of Organic and Inorganic Fertilizers on Soil Properties, Growth Yield, and Physiochemical Properties of Sunflower Seeds and Oils,” Sustain., vol. 14, no. 19, 2022, doi: 10.3390/su141912928.

B. P. Akinde, A. O. Olakayode, D. J. Oyedele, and F. O. Tijani, “Selected physical and chemical properties of soil under different agricultural land-use types in Ile-Ife, Nigeria,” Heliyon, vol. 6, no. 9, p. e05090, 2020, doi: 10.1016/j.heliyon.2020.e05090.

R. E. Enescu, L. Dincă, M. Zup, Șerban Davidescu, and D. Vasile, “Assessment of Soil Physical and Chemical Properties among Urban and Peri-Urban Forests: A Case Study from Metropolitan Area of Brasov,” Forests, vol. 13, no. 7, 2022, doi: 10.3390/f13071070.

W. Food, Soils for nutrition: state of the art. 2022. doi: 10.4060/cc0900en.

M. S. O’Donnell and D. J. Manier, “Spatial Estimates of Soil Moisture for Understanding Ecological Potential and Risk: A Case Study for Arid and Semi-Arid Ecosystems,” Land, vol. 11, no. 10, 2022, doi: 10.3390/land11101856.

T. Blesslin Sheeba et al., “Machine Learning Algorithm for Soil Analysis and Classification of Micronutrients in IoT-Enabled Automated Farms,” J. Nanomater., vol. 2022, 2022, doi: 10.1155/2022/5343965.

R. Thakur, “Recent Trends Of Machine Learning In Soil Classification : A Review,” Int. J. Comput. Eng. Res., vol. 08, no. 9, pp. 25–32, 2018.

M. Uddin and M. R. Hassan, “A novel feature based algorithm for soil type classification,” Complex Intell. Syst., vol. 8, no. 4, pp. 3377–3393, 2022, doi: 10.1007/s40747-022-00682-0.

J. Guo, K. Wang, and S. Jin, “Mapping of Soil pH Based on SVM-RFE Feature Selection Algorithm,” Agronomy, vol. 12, no. 11, p. 2742, 2022, doi: 10.3390/agronomy12112742.

N. Carvalho, L. C. Barbosa, H. Bellinaso, C. Danilo, and D. Mello, “Soil Erosion Satellite-Based Estimation in Cropland for Soil Conservation,” pp. 1–24, 2023.

A. Ingle, “Crop Recommendation Dataset.” https://www.kaggle.com/datasets/atharvaingle/crop-recommendation-dataset


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность IT congress 2023

ISSN: 2307-8162