Perbandingan Random Forest Regression dan Support Vector Regression Pada Prediksi Laju Penguapan
نویسندگان
چکیده
Memprediksi laju penguapan memiliki manfaat yang luas dalam berbagai aplikasi seperti manajemen sumber daya air, pertanian, dan lingkungan hidup. Namun untuk mendapatkan data lengkap akurat mempelajari tantangan tersendiri. Selain itu, rendahnya tingkat linieritas antara faktor meteorologi lainnya di wilayah tropis dapat menyebabkan hasil prediksi bervariasi. Tujuan dari penelitian ini adalah memprediksi harian Stasiun Klimatologi Yogyakarta dengan membandingkan kinerja dua model machine learning (ML) yaitu random forest regression (RFR) support vector (SVR) menggunakan pengamatan harian. Untuk meningkatkan akurasi prediksi, dilakukan optimasi hyperparameter metode gridsearch cross-validation mencari kombinasi terbaik. Hasil pada training menunjukkan bahwa RFR menghasilkan skor RMSE sebesar -0,67 sementara SVR kernel RBF negatif -0,57. Evaluasi lebih lanjut testing nilai R2 0,79 0,56 sedangkan koefisien determinasi (R2) 0,81 0,53. Berdasarkan perbandingan kedua disimpulkan baik Penggunaan teknik ML menjadi solusi mengisi kekosongan signifikan bidang pertanian hidrologi. Penelitian selanjutnya melibatkan pengembangan sistem informasi pemantauan pengelolaan air efektif efisien.
منابع مشابه
Support vector regression with random output variable and probabilistic constraints
Support Vector Regression (SVR) solves regression problems based on the concept of Support Vector Machine (SVM). In this paper, a new model of SVR with probabilistic constraints is proposed that any of output data and bias are considered the random variables with uniform probability functions. Using the new proposed method, the optimal hyperplane regression can be obtained by solving a quadrati...
متن کاملsupport vector regression with random output variable and probabilistic constraints
support vector regression (svr) solves regression problems based on the concept of support vector machine (svm). in this paper, a new model of svr with probabilistic constraints is proposed that any of output data and bias are considered the random variables with uniform probability functions. using the new proposed method, the optimal hyperplane regression can be obtained by solving a quadrati...
متن کاملBalanced Support Vector Regression
We propose a novel idea of regression – balancing the distances from a regression function to all examples. We created a method, called balanced support vector regression (balanced SVR) in which we incorporated this idea to support vector regression (SVR) by adding an equality constraint to the SVR optimization problem. We implemented our method for two versions of SVR: ε-insensitive support ve...
متن کاملSupport Vector Ordinal Regression
In this letter, we propose two new support vector approaches for ordinal regression, which optimize multiple thresholds to define parallel discriminant hyperplanes for the ordinal scales. Both approaches guarantee that the thresholds are properly ordered at the optimal solution. The size of these optimization problems is linear in the number of training samples. The sequential minimal optimizat...
متن کاملInterpretable support vector regression
This paper deals with transforming Support vector regression (SVR) models into fuzzy systems (FIS). It is highlighted that trained support vector based models can be used for the construction of fuzzy rule-based regression models. However, the transformed support vector model does not automatically result in an interpretable fuzzy model. Training of a support vector model results a complex rule...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Jurnal Fasilkom
سال: 2023
ISSN: ['2089-3353']
DOI: https://doi.org/10.37859/jf.v13i02.4976