Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Jurnal Biogenerasi

Analisis Komparatif Keragaman Serangga Tanah Diurnal pada Perkebunan Kopi Berdasarkan Prediksi AI dan Eksplorasi Lapangan Afandi, Aril; Winarno, Winarno; Suhada, Suhada; Maharani, Annisa Lidya; Safitri, Anggi; Saputri, Nur Ayu; Rhamadaningtyas, Nabila Aulia; Soegiharto, Yolande Cathleya; Apriani, Vivin; Fitrisyah, Asyifa Zahara; Pratama, M. Idris Afta; Vega, Cindy Ameliya; Pawaka, Arrahmaan Syah; Saputra, Rama Arsalta Bara; Amrullah, Syarif Hidayat; Parabi, M. Iqbal; Rustiati, Elly Lestari; Pratami, Gina Dania; Permatasari, Nindy; Priyambodo, Priyambodo
Jurnal Biogenerasi Vol. 10 No. 4 (2025): Volume 10 nomor 4 tahun 2025 Terbit Oktober-Desember 2025
Publisher : Universitas Cokroaminoto Palopo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30605/biogenerasi.v10i4.7121

Abstract

Soil insects play a crucial role in maintaining ecosystem balance and supporting soil fertility, particularly within coffee plantation ecosystems. This study aims to analyze the diversity of soil insects by comparing results from artificial intelligence (AI)-based predictions and field explorations to obtain a comprehensive understanding of community structure. The research was conducted in a smallholder coffee plantation located in Wiyono Village, Pesawaran Regency, Lampung. Field data were collected using the pitfall trap method, while AI-based predictions were generated utilizing a dataset derived from 14 relevant scientific publications. Data analysis employed the Shannon-Wiener diversity index (H′) to evaluate differences between predicted and observed results. The findings revealed that the AI-based prediction estimated an H′ value of 1.787 (moderate diversity), whereas the field exploration yielded an H′ value of 0.428 (low diversity). This discrepancy is influenced by dataset limitations, species dominance, and selectivity inherent in the sampling method. The results highlight the importance of integrating AI-based predictive approaches with field validation to enhance the accuracy of biodiversity assessments. This study contributes to the development of AI-driven prediction models and supports sustainable management of coffee plantation ecosystems.