Machine learning for the detection of soil pH, macronutrients, and micronutrients with crop and fertilizer recommendations

Aug 3, 2026

Upload by Ezra

A machine learning framework is developed to determine key soil parameters—soil pH, macronutrients (nitrogen, phosphorus, potassium), and micronutrients (copper, iron, zinc)—to support crop and fertilizer decision-making. Soil pH and macronutrient levels are obtained using a soil test kit, while micronutrients require assays for colorimetric determination. Spectrometric and colorimetric outputs serve as inputs to compare algorithms including support vector machines, naïve Bayes, and k-nearest neighbor for fast, high-predictive classification and regression.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages8

Reading Time20 min

AccessFree to download

Introduction

Smart agriculture and soil parameter monitoring

Role of machine learning for soil analysis

Related work and algorithm comparisons

Decision tree, regression-based approaches, and IoT agriculture systems

Machine learning for the detection of soil pH, macronutrients, and micronutrients with crop and fertilizer recommendations John Joshua Montañez1,2, Jeffrey Sarmiento2 1College of Engineering, Bicol State College of Applied Sciences and Technology, Naga City, Philippines 2College of Engineering, Batangas State University, the National Engineering University, Batangas City, Philippines Article history: Received Mar 19, 2024 Revised Oct 10, 2024 Accepted Oct 18, 2024 Keywords: Colorimetry Crop and fertilizer Machine learning Soil parameters Soil test kit Corresponding Author: The study aims to determine the levels of soil parameters such as soil pH, macronutrients, and micronutrients. After determining said parameters, the system appropriately recommends crops and fertilizers suitable for the soil samples. For soil pH and macronutrient levels, i.e., nitrogen, phosphorus, and potassium, these parameters can be detected using the soil test kit. Meanwhile, for soil micronutrients, i.e., copper, iron, and zinc, there is a need for the development of appropriate assays for colorimetric processes that can be done for the appropriate determination of said micronutrients. Comparison of available machine learning such as support vector machine algorithm, naïve Bayes algorithms, and K-nearest neighbor algorithm is a must to determine the well-fit algorithm that is considered fast and has high predictive power in classification and regression. The outputs of the colorimetric and spectrometric processes are the inputs in the machine learning activities intended for crop and fertilizer recommendation. This is an open access article under the CC BY-SA license. John Joshua Montañez College of Engineering, Bicol State College of Applied Sciences and Technology Peñafrancia Avenue, Naga City, Camarines Sur, Philippines Email: [jjfmontanez@astean.biscast.edu.ph](jjfmontanez@astean.biscast.edu.ph) Article Info ABSTRACT 1. INTRODUCTION In the worldwide setup, agriculture is considered a vital industry that continues to thrive considerably with us in the foreseeable future. The incorporation of technology in agriculture is inevitable since the role of technology is seen as favorable to the advancement of humankind, and this is visible in advances in monitoring soil parameters like humidity, temperature, and moisture, leading to an increase in the production of high-value crops. Technically, the integration of the advancement of technology, various protocols, and advances in computational paradigms in agriculture that seek to increase yields in crop production is called smart agriculture. Smart agriculture, smart farming, and agriculture 4.0 are used interchangeably [1]–[4] . Implementing various agricultural processing controlled by the internet, internet of things (IoT) represents smart agriculture, robotics, big data analytics, unmanned aerial vehicles, and artificial intelligence via machine learning and deep learning algorithms [5]–[7] . Smart agriculture, through the inculcation of information communication technology manifested in the management offarms and other areas of implementation of clean and efficient agro-industry processes, paves the way for a sustainable future of food production for the growing population worldwide. In terms of the sustainable development goals (SDGs) of the United Nations (UN), smart agriculture, in its goal to have a high and clean increase in yields, directly and certainly addresses SDG number two, which is zero hunger [6]–[8] . Success in intelligent agriculture, especially in crop production, can be attributed to proper maintenance of the soil as it is considered a core component of the environment. Thus, a substantial effort must be made to preserve it. Soil productivity and soil fertility must be studied and analyzed as this is proportional to the crop and yields. The soil paraments such as soil pH, macronutrients, i.e., nitrogen, phosphorus, and potassium, and micronutrient

FAQs

How are soil pH and macronutrient levels measured in the study?

Soil pH and macronutrients (nitrogen, phosphorus, and potassium) are detected using a soil test kit.

Why are micronutrients treated differently than pH and macronutrients?

Micronutrients (copper, iron, and zinc) require development of appropriate assays for colorimetric processes to determine their levels.

Which machine learning algorithms are compared for crop and fertilizer recommendations?

The study compares support vector machine, naïve Bayes, and k-nearest neighbor to select a well-fit model with high predictive power for classification and regression.

Aug 3, 2026

Upload by Ezra