Article Per Year (5 Year)
p-Index From 2020 - 2025
3.895
P-Index
This Author published in this journals
All Journal Abdimasku : Jurnal Pengabdian Masyarakat ABIDUMASY : Jurnal Pengabdian kepada Masyarakat Jurnal Mediakita : Jurnal Komunikasi dan Penyiaran Islam Intelmatics Menara Tebuireng : Jurnal Ilmu-Ilmu Keislaman RESLAJ: Religion Education Social Laa Roiba Journal SPEKTRA KOMUNIKA Millatuna: Jurnal Studi Islam
Anwari
Universitas Hasyim Asy'ari Tebuireng Jombang
Religion Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Mathematics Social Sciences Other

Published : 27 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Intelmatics

 1 
Optimizing Agricultural Land Fertility through Nutrient Content and pH Analysis Tamam, Moh. Badri; Anwari; Rofiuddin; Supriatin
Intelmatics Vol. 5 No. 2 (2025): July-December
Publisher : Penerbitan Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/v5i2.24051

Abstract

This research addresses the challenge of declining soil fertility in Pamekasan, East Java, by proposing a machine learning approach to improve the accuracy of soil fertility classification and provide data-driven recommendations. Conventional methods like linear regression and expert systems are limited in capturing the complexity of soil variables, leading to less accurate results. Therefore, this study compares the performance of two machine learning algorithms, Random Forest and XGBoost, in classifying soil fertility levels based on nutrient content (N, P, K, and micronutrients) and soil pH. The dataset, consisting of 880 soil samples from Pamekasan, revealed an imbalance, with the high-fertility class accounting for only 39 samples. After data preprocessing, both models were evaluated. The Random Forest model achieved an overall accuracy of 90.34%, slightly outperforming XGBoost, which reached 88.64%. Random Forest demonstrated superior performance in detecting low-fertility land (recall 0.97) and medium-fertility land (precision 0.93, recall 0.88). For the high-fertility minority class, Random Forest showed better recall (0.60) than XGBoost (0.40), while maintaining perfect precision (1.00). The study concludes that Random Forest is the optimal model for classifying soil fertility in Pamekasan. These findings provide a basis for more precise, efficient, and sustainable fertilization recommendations, which are expected to help farmers optimize productivity and support the sustainability of the local agricultural ecosystem by reducing excessive fertilizer use.
Co-Authors Achfaz Fauzi Advan Navis Zubaidi Ahmad Fakhruddin Fajrul Islam Ahmad Gunawan Imani Ainun Fitri Mughiroh Alkhoir, Difa Anjabi, Muhammad Juhan Putra Sabuth As'ad, Muhammad Atika Suri, Putri Sukma BAMBANG SUJATMIKO Fajrul Falah Haryanti, Nanda Kumala Hasnah Zein Khafidz Hidyatullah kristanti, Yuli fuji kristanti Lathifatul Sholikah Lilly Nabillah M. Sahrun Ni’am Malayati, Robi'ah Machtumah Moh. Badri Tamam Moh. Slamet Muhammad Muhammad Rafli Dwi Nur Alam Alam Nanda Kumala Haryanti Nisrina Salsabila Ridha Putri Sukma Atika Suri Ridha, Nisrina Salsabila Robi'ah Machtumah Malayati Robi’ah Machtumah Malayati Rofiuddin Sayidah Afyatul Masruroh Shofi Yuli Setiani Sholikah, Lathifatul Slamet Slamet, Moh. Suhari SUPRIATIN