Algoritma Random Forest  Algoritma Random Forest Untuk Prediksi Perkerasan Tanah : Algoritma Random Forest

Hanifah  Asnur; Rini   Yunita; Arif Rizki Marsa

doi:10.55382/jurnalpustakaai.v5i2.1082

Penulis

H Asnur Sekolah Tinggi Teknologi Payakumbuh
Rini Yunita Sekolah Tinggi Teknologi Payakumbuh
Arif Rizki Marsa Politeknik Negeri Padang

DOI:

https://doi.org/10.55382/jurnalpustakaai.v5i2.1082

Kata Kunci:

Random Forest, CBR, kepadatan tanah, machine learning, perkerasan jalan

Abstrak

Prediksi kepadatan tanah dasar sangat penting dalam perancangan perkerasan jalan. penelitian ini mengintegrasikan eksperimen laboratorium dengan pendekatan machine learning, khususnya algoritma Random Forest, untuk memprediksi nilai California Bearing Ratio (CBR) berdasarkan parameter pemadatan tanah. Sampel tanah diuji menggunakan metode Standard Proctor guna menentukan kadar air optimum dan berat isi kering maksimum, kemudian dilanjutkan dengan pengujian CBR di laboratorium pada variasi energi tumbukan (10, 25, dan 56 kali). Model Random Forest kemudian dilatih menggunakan variabel input berupa kadar air, berat isi kering, dan jumlah tumbukan, dengan nilai CBR sebagai variabel output. Hasil menunjukkan bahwa model menghasilkan tingkat akurasi prediksi yang tinggi (R² > 0,90) dan memberikan estimasi yang sangat mendekati hasil pengujian laboratorium. Pendekatan ini menunjukkan potensi yang signifikan dalam menyederhanakan dan mempercepat analisis teknis pada desain tanah dasar perkerasan.

Unduhan

Data unduhan belum tersedia.

Biografi Penulis

Arif Rizki Marsa, Politeknik Negeri Padang

Referensi

Ikeagwuani, C. C. (2021). Estimation of modified expansive soil CBR with multivariate adaptive regression splines, random forest and gradient boosting machine. Innovative Infrastructure Solutions, 6(4), 199.

Doan, D. Q., Vu, H. C., Nguyen, V. T., Vu, T. Q., Tran, V. T., & Chu, V. T. (2024). An atomic-scale insight into mechanical enhancement and frictional properties of amorphous/graphene multilayers. Tribology International, 197, 109783.

Hasan, S., & Ansary, M. A. (2024). Development of Empirical Correlations Between CPT and Other Soil Parameters Within DMDP Area, Bangladesh. Indian Geotechnical Journal, 1-16.

Kassa, S. M., Wubineh, B. Z., Geremew, A. M., Azmatch, T. F., & Kumar, N. D. (2023, August). Prediction of Compaction Parameters Based on the Atterberg Limit by Using a Machine Learning Approach. In International Conference on Advances of Science and Technology (pp. 133-146). Cham: Springer Nature Switzerland.

Pule, B. B., & Yendaw, J. A. (2024). The effect of geotechnical soil properties on cbr value. AI in Civil Engineering, 3(1), 1-11.

Tamassoki, S., Daud, N. N. N., Wang, S., & Roshan, M. J. (2023). CBR of stabilized and reinforced residual soils using experimental, numerical, and machine-learning approaches. Transp Geotech 42: 101080.

Trong, D. N., Dang, P. N., ??lu, ?., & Long, V. C. (2022). A molecular dynamics study concerning the effect of high-temperature and high-pressure on the structure and phase transition of Fe 2 O 3 material. AIMS Materials Science, 9(3), 406-429.

Iqbal, M., Onyelowe, K. C., & Jalal, F. E. (2021). Smart computing models of California bearing ratio, unconfined compressive strength, and resistance value of activated ash-modified soft clay soil with adaptive neuro-fuzzy inference system and ensemble random forest regression techniques. Multiscale and Multidisciplinary Modeling, Experiments and Design, 4(3), 207-225.

JHo, L. S., & Tran, V. Q. (2022). Machine learning approach for predicting and evaluating California bearing ratio of stabilized soil containing industrial waste. Journal of Cleaner Production, 370, 133587.

Sapta, W., Harianto, Y., & Gofar, N. (2023). CBR Correlation with Index and Compaction Properties of Soil. Indonesian Geotechnical Journal, 2(3), 179-188.