Predicting optimal Fertilizers using Machine Learning and Deep Learning

DOI

10.2991/978-94-6239-693-7_34How to use a DOI?

Keywords

Precision agriculture; Machine learning; Fertilizer recommendation; Random forest; MAP3; Crop yield; Soil health; Nutrient management

Abstract

The use of machine learning (ML) methods is the new wave of precision agriculture that will transform the traditional methods of farming by refining fertilizer recommendations, increasing crop yields, and reducing environmental impacts. This study provides a comparative analysis of the ML and deep learning algorithms to the problem of fertilizer recommendation with the use of the 10,098 samples that have certain attributes such as nitrogen, phosphorus, potassium, moisture, humidity, temperature, crop type, and soil type. The dataset was divided into training and testing subsets after a thorough preprocessing of data and analysis of the exploratory data. After that, various models, such as random forest, gradient boosting, SVM, logistic regression, k-nearest neighbors, and deep learning were trained and evaluated based on the Mean Average Precision at 3 (MAP3) metric. The results reveal that the random forest algorithm was better performing with a MAP3 score of 0.2805, which justifies its application in the management of site-specific nutrients in heterogeneous tabular data. The MAP3 index enables a consistent prioritization of fertilizer recommendations, hence helping farmers in making adaptive decision-making. This study highlights how ensemble machine learning methods can be used to achieve precision agriculture, and indeed indicates that more needs to be explored in the advanced deep learning architecture to come up with a cost effective and scalable solution.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Suraj Pal Singh
AU  - Gurmeet Kaur Saini
AU  - Rakesh Kumar Arora
AU  - Partibha Dabas
PY  - 2026
DA  - 2026/06/16
TI  - Predicting optimal Fertilizers using Machine Learning and Deep Learning
BT  - Proceedings of the International Conference on Intelligent Systems for a Sustainable Future (ISSF 2026)
PB  - Atlantis Press
SP  - 338
EP  - 345
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-693-7_34
DO  - 10.2991/978-94-6239-693-7_34
ID  - Singh2026
ER  -