Claim Missing Document
Check
Articles

Found 40 Documents
Search

HYDROLOGICAL EXTREMES AND WATER ALLOCATION IN TROPICAL RIVER BASINS: EVIDENCE FROM THE JENEBERANG RIVER, MAKASSAR Abd Rakhim Nanda
Nusantara Hasana Journal Vol. 3 No. 7 (2023): Nusantara Hasana Journal, December 2023
Publisher : Yayasan Nusantara Hasana Berdikari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59003/nhj.v3i7.2031

Abstract

This study proposes an adaptive water allocation framework based on the pipeline P(t)→SPI(t)→A(t), with SPI serving as a control variable to represent hydrological conditions probabilistically. Analysis shows that rainfall is non-stationary and dominated by stochastic variability, making a mean-based approach unrepresentative. Integrating SPI enables dynamic adjustment of allocations to actual conditions, reducing the deficit by 12.96% and increasing efficiency from 46.32% to 53.49%. Validation of the dataset shows high consistency with the presence of systematic scale bias, making it more suitable for anomaly-based analysis. Sensitivity analysis identifies bounded responsiveness, where the system is adaptive under normal conditions but remains stable under extreme conditions. Conceptually, this study transforms the SPI into a decision variable, thereby establishing a causal relationship between hydroclimatic variability and allocation decisions and enhancing the system’s resilience to drought risk.
QUANTIFYING RAINFALL - EVAPOTRANSPIRATION IMBALANCE AND IRRIGATION WATER DEFICIT IN THE BANTIMURUNG IRRIGATION AREA, MAROS, INDONESIA Abd Rakhim Nanda
Nusantara Hasana Journal Vol. 4 No. 1 (2024): Nusantara Hasana Journal, Juny 2024
Publisher : Yayasan Nusantara Hasana Berdikari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59003/nhj.v4i1.2032

Abstract

This study quantifies irrigation water deficit in the Bantimurung Irrigation District (Maros, Indonesia) by integrating rainfall-evapotranspiration imbalance into a hydrological-agronomic water balance. Monthly rainfall (CHIRPS) and reference evapotranspiration (Open-Meteo) for 2000–2024 were combined with crop coefficients and a local planting calendar to estimate effective rainfall and net irrigation requirement (NIR). Despite cumulative rainfall of 81,077.6 mm exceeding crop evapotranspiration (34,450.6 mm; 2.35:1), deficits occurred in 96 of 300 months (32%), concentrated in July–October. Total NIR was ~9,044 mm (≈361.8 mm yr⁻¹), with 97.35% accruing in the dry season and peak demand in August–September. The maximum monthly deficit was 200.93 mm (September 2023) and the most severe year was 2015 (711.12 mm).
A SCENARIO-BASED HYDROLOGICAL SIMULATION FRAMEWORK FOR CLIMATE-RESILIENT IRRIGATION WATER ALLOCATION IN TROPICAL WATERSHEDS Abd Rakhim Nanda
Nusantara Hasana Journal Vol. 5 No. 5 (2025): Nusantara Hasana Journal, October 2025
Publisher : Yayasan Nusantara Hasana Berdikari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59003/nhj.v5i5.2033

Abstract

Rainfall variability and climate uncertainty increasingly affect irrigation water availability in tropical watersheds. This study develops a scenario-based hydrological simulation framework for climate-resilient irrigation water allocation. The framework integrates rainfall scenario development, runoff estimation, evapotranspiration-based crop water requirement, water availability assessment, and monthly water balance analysis. Five rainfall scenarios were simulated, consisting of normal rainfall, moderate rainfall deficit, severe drought, extreme drought, and extreme rainfall conditions. The results show that reduced rainfall substantially decreases water availability and increases irrigation deficit during the dry season. Irrigation reliability declined from 75% under normal conditions to 60%, 42%, and 25% under moderate, severe, and extreme drought scenarios, respectively. In contrast, the extreme rainfall scenario increased reliability to 85%, although it may intensify runoff and flood risk. The proposed framework supports adaptive irrigation scheduling, crop calendar adjustment, storage optimization, and climate-resilient water allocation planning.
RAINFALL–RUNOFF SIMULATION FOR SUSTAINABLE IRRIGATION WATER MANAGEMENT IN TROPICAL AGRICULTURAL CATCHMENT Abd Rakhim Nanda
Nusantara Hasana Journal Vol. 5 No. 11 (2026): Nusantara Hasana Journal, April 2026
Publisher : Yayasan Nusantara Hasana Berdikari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59003/nhj.v5i11.2034

Abstract

Rainfall–runoff processes play a crucial role in determining irrigation water availability in tropical agricultural catchments. This study develops a rainfall–runoff simulation framework for sustainable irrigation water management by integrating rainfall characterization, SCS-CN runoff estimation, runoff coefficient analysis, effective runoff availability, irrigation water demand, water balance, Surplus–Deficit Ratio, and Irrigation Sustainability Index. Monthly rainfall data were used to estimate runoff depth and runoff-derived water availability, while irrigation demand was evaluated based on crop water requirement and effective water availability. The results show that runoff generation is highly seasonal, with high runoff coefficients during wet months and low runoff response during dry months. The ISI results indicate highly sustainable irrigation conditions in January, February, and December, sustainable conditions in March and November, and critical conditions from June to September. The proposed framework supports runoff harvesting, storage optimization, rotational irrigation, crop calendar adjustment, and priority-based water allocation.
Simulasi Komputasi Gerusan Terhadap Kemiringan Baffle Block Pada Bangunan Peredam Energi USBR Type IV Bangunan Spillway Djunur, Lutfi Hair; Nanda, Abd Rakhim
Paulus Civil Engineering Journal Vol. 8 No. 2 (2026): Paulus Civil Engineering Journal, Juni 2026
Publisher : Universitas Kristen Indonesia Paulus

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52722/4md0av05

Abstract

A spillway is a hydraulic structure designed to regulate the flow of water. The energy dissipation structure of a spillway constitutes an essential component of a dam system, functioning to dissipate the kinetic energy of flowing water downstream of the spillway. Energy dissipating devices, such as baffle blocks, are commonly utilized to enhance operational efficiency and to minimize the potential for downstream scour. This study employs computational simulation to investigate the scour behavior resulting from the placement of baffle blocks within the USBR Type IV stilling basin of a spillway, particularly in relation to changes in scour patterns. The research was conducted in a laboratory setting using a scaled physical model to represent the spillway. The experimental results were subsequently validated using SURFER software to develop a numerical model of the USBR Type IV energy dissipation channel. The numerical simulations were carried out using three discharge variations and three configurations of baffle blocks, consistent with the laboratory setup. The analysis evaluates the resulting scour patterns due to the presence of baffle blocks within the stilling basin, assessing whether the simulation outcomes align with experimental observations or exhibit discrepancies. It is expected that this study will provide a more comprehensive understanding of how variations in discharge and the configuration of baffle block placement within a USBR Type IV stilling basin influence the resulting scour patterns in the downstream channel.  
Optimasi Kinerja Arsitektur CNN Ringan Menggunakan Pendekatan Bayesian untuk Identifikasi Skrip Bima Dayang Aisyah; Muhammad Faisal; Lukman Anas; Abd Rakhim Nanda; Syadiah Nor Wan Shamsuddin; Muhammad Syafaat S. Kuba
Buletin Sistem Informasi dan Teknologi Islam (BUSITI) Vol 7, No 2 (2026)
Publisher : Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/busiti.v7i2.3462

Abstract

Identifikasi aksara daerah penting untuk mendukung pelestarian budaya digital, namun masih terkendala keterbatasan dataset, kemiripan karakter, dan kebutuhan model yang efisien. Penelitian ini mengoptimasi arsitektur Lightweight CNN menggunakan Bayesian Optimization untuk identifikasi aksara Bima. Dataset terdiri atas 6.190 citra aksara Bima dalam 44 kelas, mencakup aksara Bima baru dan lama. Model menggunakan MobileNetV3-Large sebagai backbone dengan optimasi learning rate, dropout, batch size, dan konfigurasi fine-tuning melalui Tree-structured Parzen Estimator. Hasil eksperimen menunjukkan accuracy 93,06%, precision 92,26%, recall 92,55%, dan F1-score 91,91%, lebih unggul dibanding machine learning tradisional, CNN konvensional, dan beberapa CNN ringan modern. Target accuracy 90% dicapai pada trial keempat. Dengan 3.253.676 parameter dan waktu inferensi 63,35 ms per citra, model ini terbukti akurat, efisien, dan berpotensi diterapkan pada digitalisasi manuskrip serta OCR aksara daerah.
A Calibrated ROI-Aware Hybrid CNN-Transformer for Kidney Stone Presence Classification on Heterogeneous Axial CT Images Muh Ilham Akbar; Muhammad Faisal; Desi Anggreani; Abd Rakhim Nanda; Try Gustaf Said; Muhammad Syafaat S. Kuba
Buletin Sistem Informasi dan Teknologi Islam (BUSITI) Vol 7, No 2 (2026)
Publisher : Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/busiti.v7i2.3463

Abstract

Batu ginjal merupakan penyebab umum nyeri pinggang akut, dan CT non-kontras menjadi standar referensi untuk mendeteksi kalkulus. Pada penelitian ini, istilah heterogen merujuk pada variasi protokol akuisisi antarrumah sakit, seperti perbedaan dosis radiasi, ketebalan irisan, rekonstruksi, dan bidang pandang, yang dapat mengubah tampilan citra serta menurunkan konsistensi pembacaan. Penelitian ini mengusulkan model hibrida CNN-Transformer yang sadar ROI (implisit) untuk klasifikasi keberadaan batu ginjal pada citra CT aksial heterogen. Arsitektur menggabungkan EfficientNet-B3, encoder Transformer ringan, dan Convolutional Block Attention Module (CBAM) tanpa anotasi ROI manual. Dataset terdiri dari 3.364 citra (1.577 batu, 1.787 non-batu) dengan pemisahan bertingkat 70/15/15. Evaluasi mencakup akurasi, presisi, sensitivitas, spesifisitas, F1, ROC-AUC, PR-AUC, inspeksi kalibrasi, dan audit Grad-CAM. Hasil menunjukkan bahwa penambahan Transformer meningkatkan kinerja dibanding baseline CNN, sedangkan CBAM menggeser profil kesalahan ke sensitivitas yang lebih tinggi. Varian Hybrid+Attention mencapai akurasi 0,9861, F1 0,9851, dan ROC-AUC 0,9967 pada set uji, dengan jumlah negatif palsu lebih rendah dibanding varian hibrida tanpa perhatian. Temuan ini menunjukkan potensi model sebagai alat bantu dokter untuk triase dan pembacaan awal yang lebih konsisten pada data lintas protokol, meskipun validasi eksternal, pemisahan berbasis pasien, dan metrik kalibrasi kuantitatif masih diperlukan sebelum klaim kesiapan klinis.
Analisis Perbandingan Kinerja Arsitektur CNN VGG19, ResNet50, EfficientNetB0, dan MobileNetV2 untuk Deteksi Wajah Asli dan Wajah Buatan AI Erika Yanti; Muhammad Faisal; Titin Wahyuni; Abd Rakhim Nanda; Nurnawaty Nurnawaty; Rizki Yusliana Bakti
Buletin Sistem Informasi dan Teknologi Islam (BUSITI) Vol 7, No 2 (2026)
Publisher : Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/busiti.v7i2.3465

Abstract

Perkembangan Generative Artificial Intelligence (GenAI) memungkinkan pembuatan citra wajah sintetis yang sangat menyerupai wajah asli, sehingga menimbulkan tantangan terhadap keaslian informasi digital, privasi, dan keamanan identitas. Penelitian ini mengevaluasi kinerja empat arsitektur Convolutional Neural Network (CNN), yaitu VGG19, ResNet50, EfficientNetB0, dan MobileNetV2, dalam klasifikasi wajah asli dan wajah hasil generasi AI. Dataset yang digunakan adalah HFD-8000 yang terdiri atas 8.000 citra wajah dengan skenario klasifikasi biner. Tahapan penelitian meliputi prapemrosesan data, pembagian dataset, augmentasi, penanganan ketidakseimbangan kelas, serta pelatihan model menggunakan transfer learning. Evaluasi dilakukan menggunakan accuracy, precision, recall, F1-score, ROC-AUC, dan confusion matrix. Hasil penelitian menunjukkan bahwa ResNet50 dan VGG19 memperoleh performa terbaik dengan akurasi 99,50% dan macro F1-score 99,22%. EfficientNetB0 mencapai akurasi 97,83% dan F1-score 96,61%, sedangkan MobileNetV2 memperoleh akurasi 92,58% dan F1-score 86,40%. Secara keseluruhan, ResNet50 menjadi model paling optimal karena menunjukkan keseimbangan antara akurasi, stabilitas, efisiensi, dan keandalan dalam klasifikasi wajah asli dan sintetis.
Eksperimentasi Peran Serat Alam Pada Tanah Lempung Dalam Upaya Peningkatan Infiltrasi Dan Plastisitas Tanah Nurnawaty; Abd Rakhim Nanda; Tendri Ajeng; Intan Fadillah
Jurnal Karajata Engineering Vol. 5 No. 1 (2025): 2025
Publisher : Fakultas Teknik Universitas Muhammadiyah Parepare

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31850/karajata.v5i1.3446

Abstract

Clay soil consists of a type with limited load-bearing ability and low shear strength, thus it is essential to enhance the soil's stability, as this is influenced by the moisture level. The amount of water obtained by the soil depends on the soil's ability to absorb and channel the water received from the soil surface to the lower layers. Therefore, alternative materials are needed to improve the properties of the soil. This study aims to determine the effect of adding natural fibers on the infiltration and plasticity of clay soil. This research was a laboratory based testing, where infiltration testing was carried out using channel media and soil stability testing using the Atterbeg method. The addition of natural fibers to clay soil affects the infiltration discharge. The highest infiltration discharge is clay soil with the addition of rice husks and the lowest infiltration discharge is clay soil with a mixture of coconut fiber. Adding rice husks to clay soil can reduce the plastic index number which is 6%.
Analisis Kontribusi Deteksi Tangan dan Ekstraksi Landmark untuk Pengenalan Alfabet BISINDO Wa Nanda Sulystrian; Muhammad Faisal; Fahrim Irhamna Rachman; Abd Rakhim Nanda; Rizki Yusliana Bakti; Muhammad Syafaat S. Kuba; Andi Makbul Syamsuri
Buletin Sistem Informasi dan Teknologi Islam (BUSITI) Vol 7, No 3 (2026)
Publisher : Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/busiti.v7i3.3506

Abstract

Komunitas tunarungu menghadapi hambatan dalam aspek bahasa dan komunikasi sehingga membutuhkan dukungan teknologi yang sesuai dengan karakteristik visual mereka. Kondisi tersebut menunjukkan pentingnya pengembangan teknologi untuk mendukung akses komunikasi yang lebih inklusif melalui pengenalan Bahasa Isyarat Indonesia (BISINDO). Penelitian ini menganalisis kontribusi deteksi tangan dan ekstraksi landmark terhadap performa pengenalan alfabet BISINDO menggunakan pendekatan berbasis computer vision. Sistem yang diusulkan mengintegrasikan YOLOv8 untuk deteksi tangan, MediaPipe Hands untuk ekstraksi dua puluh satu landmark, normalisasi landmark, serta Multi-Layer Perceptron sebagai model klasifikasi. Evaluasi dilakukan menggunakan dataset berisi 1066 citra alfabet BISINDO dari 26 kelas melalui tiga skenario eksperimen. Hasil penelitian menunjukkan bahwa kombinasi deteksi tangan dan normalisasi landmark menghasilkan performa terbaik dengan nilai accuracy 0.915, precision 0.913, recall 0.915, dan F1-score 0.896, serta meningkatkan accuracy 14.8% dibandingkan pendekatan tanpa deteksi tangan. Temuan ini menunjukkan bahwa deteksi tangan dan representasi landmark berkontribusi penting terhadap peningkatan akurasi sistem. Pendekatan yang diusulkan berpotensi diterapkan pada aplikasi penerjemah alfabet BISINDO berbasis kamera secara real-time untuk mendukung komunikasi yang lebih inklusif bagi komunitas tunarungu di Indonesia.
Co-Authors Abd Rasyid Jalil Abd. Rahman Bahtiar, Abd. Rahman Abdul Rasyid Jalil Abdul Rasyid Jalil Adrian Agusalim, Agusalim Agussalim Amrullah Mansida Andi Alyah Ayu Mariska Waris Andi Bunga Tongeng Andi Chadijah Andi Chadijah Andi Makbul Syamsuri Andi Sukri Syamsuri Anita Anita Asrianti Syarif Asriyanti Syarif, Asriyanti Auliafitri, Nur Bahtiar, Elbu Bakti, Rizki Yusliana Besse Emmy Saphira Burhanuddin Chadijah, Andi Dayang Aisyah Desi Anggreani Djunur, Lutfi Hair Eky Sandi Erika Yanti Fahrim Irhamna Rachman Fauzi Ahmad Muda Fitri Indah Yani Fitri Indah Yani, Fitri Indah Habibur Fathur Rahman Hartono Bancong Hartono Bancong Hartono Bancong Ibrahim, Juliani Ilham Jaya Ilham Jaya Ilham Jaya Indriyanti Intan Fadillah Kasmawati Kasmawati Khafifa Khafifa Khafifa, Khafifa LUKMAN ANAS Lutfi Hair Djunur M Agusalim Malkam, Andi Muflih Mansida, Amrullah Mirna Safitri Muh Ilham Akbar Muh. Yunus Ali Muhaemina Muhamemina Muhammad Faisal Muhammad Syafaat S. Kuba Nasir, Sri Wahyuni Nawang, Nurnawaty Nur Insana Salam Nur Insana Salam Nurinsana Salam Nurinsana Salam Nurnawaty Nurul, Nurul Mutmainnah Praja, Soemitro Emin Putri Diana Rahmat Muhammad Rahmat Muhammad Rahmat Muhammad Rahmi Rahmi Rahmi Rahmi Rahmi Rahmi Rahmi Rahmi Rahmi Rahmi Rahmi, Andi Chadijah Rian Sophian S Syamsia Saiful Sirajuddin Sirajuddin Sulvahendra Sulvahendra Syadiah Nor Wan Shamsuddin Syah, Erwin Syamsiar, Syamsiar Tendri Ajeng Titin Wahyuni Tongeng, Andi Bunga Try Gustaf Said Wa Nanda Sulystrian Yayu Sulistiawati Yusril Yusril Yusril Yusril Zhafira Zalzabila