Fuzzy logic driven real time fertiliser recommendation system with internet of things-integrated soil and environmental sensor suite

Precision nutrient management is essential for improving crop productivity while minimising fertiliser misuse, production costs and environmental impacts. This paper presents a low-cost, portable and real-time fertiliser recommendation system that integrates an Internet of Things (IoT)-based soil and environmental sensor suite with a fuzzy logic inference engine. The proposed system acquires key soil parameters, including nitrogen (N), phosphorus (P), potassium (K), pH and electrical conductivity (EC), along with environmental data and geolocation information. Sensor readings are calibrated and processed to estimate nutrient deficiencies and soil conditions. A fuzzy inference system utilises crop type, crop growth stage and nutrient deficiency percentages as inputs to generate crop-specific fertiliser recommendations for urea, diammonium phosphate (DAP), single super phosphate (SSP) and muriate of potash (MOP). An additional pH reclamation module recommends suitable amendments such as lime or gypsum. To enhance usability, a mobile application and Python-based dashboard were developed, enabling users with no prior agricultural expertise to select the crop and growth stage, deploy the sensor in the field and receive actionable recommendations, including fertiliser quantities, estimated costs and labour requirements. The system was validated using 100 soil samples collected from Southern India. The fuzzy logic output was tested across more than 40 crops and all four growth stages; however, the fuzzy-versus-conventional mathematical comparison is presented for 10 representative soil samples using sugarcane at the basal stage to provide a uniform comparison. Experimental results showed that the fuzzy recommendations followed the same recommendation trend as conventional mathematical calculations, with quantitative differences varying by fertiliser and sample. The proposed framework demonstrates a practical and scalable solution for real-time, in-field nutrient management and informed agricultural decision-making.

Authors

Institutions

Publication Details

Journal
Plant Science Today
Published
2026-11-16
DOI
https://doi.org/10.14719/pst.16617
Primary Topic
Smart Agriculture and AI
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Fuzzy logic driven real time fertiliser recommendation system with internet of things-integrated soil and environmental sensor suite

Sathees Kumar Kathirvel, R. Ranjith Pillai, S R Angelin, R T S Raja et al.
2 links
Plant Science Today
Smart Agriculture and AI
article

Fuzzy logic driven real time fertiliser recommendation system with internet of things-integrated soil and environmental sensor suite

Sathees Kumar Kathirvel, R. Ranjith Pillai, S R Angelin, R T S Raja, D Ishaan
article en

Abstract

Precision nutrient management is essential for improving crop productivity while minimising fertiliser misuse, production costs and environmental impacts. This paper presents a low-cost, portable and real-time fertiliser recommendation system that integrates an Internet of Things (IoT)-based soil and environmental sensor suite with a fuzzy logic inference engine. The proposed system acquires key soil parameters, including nitrogen (N), phosphorus (P), potassium (K), pH and electrical conductivity (EC), along with environmental data and geolocation information. Sensor readings are calibrated and processed to estimate nutrient deficiencies and soil conditions. A fuzzy inference system utilises crop type, crop growth stage and nutrient deficiency percentages as inputs to generate crop-specific fertiliser recommendations for urea, diammonium phosphate (DAP), single super phosphate (SSP) and muriate of potash (MOP). An additional pH reclamation module recommends suitable amendments such as lime or gypsum. To enhance usability, a mobile application and Python-based dashboard were developed, enabling users with no prior agricultural expertise to select the crop and growth stage, deploy the sensor in the field and receive actionable recommendations, including fertiliser quantities, estimated costs and labour requirements. The system was validated using 100 soil samples collected from Southern India. The fuzzy logic output was tested across more than 40 crops and all four growth stages; however, the fuzzy-versus-conventional mathematical comparison is presented for 10 representative soil samples using sugarcane at the basal stage to provide a uniform comparison. Experimental results showed that the fuzzy recommendations followed the same recommendation trend as conventional mathematical calculations, with quantitative differences varying by fertiliser and sample. The proposed framework demonstrates a practical and scalable solution for real-time, in-field nutrient management and informed agricultural decision-making.

Plant Science TodayVol. 13(sp9)
SRM Institute of Science and Technology (IN)
Zero hunger
Smart Agriculture and AI
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon