Claim Missing Document
Check
Articles

Found 23 Documents
Search

Explainable Machine Learning for Long-Term Monthly Hydroclimatic Forecasting and Extreme-Event Detection Arif Fadillah; Markani Pato; Nuraida Latif; Benny Leornard Encrico Panggabean; Muhammad Rizal; Mursalim Mursalim; Muhajirin Muhajirin
Journal of System and Computer Engineering Vol 7 No 3 (2026): JSCE: July 2026
Publisher : Universitas Pancasakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61628/jsce.v7i3.2741

Abstract

Long-term hydroclimatic prediction in arid urban environments remains methodologically demanding because monthly records are often intermittent, highly seasonal, zero-inflated, and dominated by rare but consequential extreme events. Using a 121-year monthly hydroclimatic record for Makkah, Saudi Arabia, spanning January 1901 to December 2021, this study develops an explainable hybrid machine-learning framework for monthly forecasting, seasonal diagnostics, and extreme-event detection. The dataset contains 1,452 monthly observations with a mean value of 6.19, median of 3.00, standard deviation of 8.05, and maximum of 52.00, indicating a strongly skewed distribution. Exploratory analysis reveals pronounced seasonality: November, December, and January exhibit the highest hydroclimatic values, whereas June is consistently dry across the full record. A temporal feature set was constructed using lag variables, rolling statistics, annual seasonal memory, cyclical month encodings, and trend indicators. Several predictive models were evaluated, including Random Forest, Extra Trees, Histogram Gradient Boosting, XGBoost, and a hybrid SARIMA–Random Forest residual-correction model. Extra Trees achieved the best forecasting performance on the holdout period, with MAE = 2.997, RMSE = 5.603, sMAPE = 57.669%, and R² = 0.518. Extreme-event detection was performed using a 90th-percentile threshold of 17.68, identifying 146 extreme months over the full record. The best classification trade-off was obtained by Histogram Gradient Boosting, while Random Forest produced the highest ROC-AUC. SHAP-based interpretation demonstrates that seasonal phase variables and annual memory features dominate model behaviour, especially month_cos, month_sin, same_month_last_year, and lag_12. The findings show that interpretable ensemble learning can provide a more transparent and operationally relevant framework than accuracy-only forecasting for arid-region hydroclimatic risk assessment.
Implementation of the Andragogy Approach in the Service Program for Islamic Boarding School Alumni Khasani, M. Taufan; Muhajirin, Muhajirin; Munir, Munir
Scaffolding: Jurnal Pendidikan Islam dan Multikulturalisme Vol. 7 No. 3 (2025): Pendidikan Islam dan Multikulturalisme
Publisher : Institut Agama Islam Sunan Giri (INSURI) Ponorogo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37680/scaffolding.v7i3.8178

Abstract

This study aims to analyze the implementation of the andragogy approach in the alumni service program of Islamic boarding schools as an effort to prepare quality human resources. The focus of the study is directed at the construction of program inputs, processes, and outputs with an emphasis on the principles of adult learning. This study is a qualitative, multisite study designed to gain an in-depth understanding of the application of the andragogical approach in the context of Islamic boarding school education in various locations. The research was conducted at several Islamic boarding schools in the South Sumatra region, including Ogan Ilir Regency, Ogan Komering Ilir Regency, and Palembang City, which have a strong tradition of organizing alumni service programs. Data were collected through in-depth interviews, observations, and documentation. Data sources consisted of alumni who participated in the community service program, pesantren leaders, supervising ustadz, and the surrounding community who interacted directly with program participants. Data analysis was conducted using Miles and Huberman's interactive model, through the stages of data reduction, data presentation, and conclusion drawing, which were verified through triangulation. The results of the study show that the input aspect is reflected in the readiness, motivation, and learning experiences of alumni, which are the main assets in adult learning. The process aspect shows the application of andragogical principles such as independent learning, problem-solving orientation, and active involvement in teaching and organizational tasks. Meanwhile, the output aspect shows the development of alumni competencies as prospective educators and community leaders, marked by increased pedagogical skills, leadership capacity, and social responsibility. This study concludes that alumni service programs designed with an andragogical perspective can improve the quality of Islamic boarding school graduates and contribute significantly to strengthening Islamic education. These findings emphasize the importance of strengthening Islamic boarding school programs through contextual andragogical strategies so that the potential of alumni can be optimized in facing contemporary educational and social challenges.
EVALUASI TERHADAP PERAN SERTA STRATEGI TEPAT DALAM PENGELOLAAN PPN MUARA ANGKE Rosalia, Ayang Armelita; Minsaris, La Ode Alam; Fawaz, Fawaz; Asnawiah, Lathifah Putri; Muhajirin, Muhajirin
Jurnal Pendidikan Perikanan Kelautan (Journal of Fisheries and Maritime Studies) Vol 2, No 1 (2022): Juni 2022
Publisher : Universitas Pendidikan Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17509/jppk.v2i1.90827

Abstract

PPN or Muara Angke Fish Landing Base is a port located in Jakarta precisely in Pluit Penjaringan DKI Jakarta since 1977. The operation of PPN Muara Angke there are several problems that exist and most importantly problems regarding ships that carelessly in making fish landings, not making landings at ports or fish landing bases. Plus the problem of facilities that have not been utilized to the maximum. Obtaining a solution to the problems in MUARA Angke VAT requires analysis and also the right strategy in the development of MUARA Angke VAT. The research was conducted based on secondary data in 2009 using several methods such as Extand, Analysis, Strategy, Analytical Hierarchy Process by utilizing Expert Choice. The final result resulted in the condition of existing facilities there Muara Angke Fish Landing Base should be maintained and carried out development in focus, especially on the pier. The most used variable in this study is variable A3 as Supporting Facility in B1 in the form of port facilities. This study uses 5 strategies to obtain development in priority, one of which is the establishment of institutions in PPN Muara Angke.