Enhancing relative humidity modelling using L2 regularization updates
Abdellah Ben Yahia1, Iman Kadir2, Abdelaziz Abdallaoui2
1Laboratory of Analytical Chemistry and Electrochemistry, Faculty of Sciences, Processes and Environment Team, URL-CNRST N 13, Moulay Ismail University, Meknes, Morocco. abd.benyahia@edu.umi.ac.ma.
Scientific Reports
|April 28, 2025
Summary
L2 regularization, combined with PCA and SOM, effectively prevents overfitting in artificial neural networks (ANNs) for meteorological modeling. This approach enhances prediction accuracy for relative humidity by optimizing model parameters.
Area of Science:
- Meteorology
- Computer Science
- Data Science
Background:
- Overfitting is a common challenge in artificial neural networks (ANNs), leading to reduced generalization performance.
- Accurate prediction of meteorological variables, such as relative humidity, is crucial for various applications.
- Principal Component Analysis (PCA) and Self-Organizing Maps (SOM) are valuable tools for analyzing complex meteorological datasets.
Purpose of the Study:
- To investigate the efficacy of L2 regularization in mitigating overfitting in ANNs for meteorological data analysis.
- To evaluate the impact of the regularization coefficient (Lambda) on model performance and data distribution.
- To explore the synergistic benefits of combining PCA, SOM, and L2 regularization for enhanced relative humidity prediction.
Main Methods:
- Utilized meteorological data from Tangier (1985-2022) comprising eight variables influencing relative humidity.
- Applied Principal Component Analysis (PCA) to identify key correlations within the dataset.
- Employed Self-Organizing Maps (SOM) to uncover nuanced data structures and complex relationships.
- Implemented L2 regularization with varying Lambda values during the training of Kohonen and Multi-Layer Perceptron (MLP) networks.
Main Results:
- PCA revealed significant correlations between variables like precipitation and relative humidity, but had limitations with non-linear relationships.
- SOM successfully complemented PCA by highlighting intricate data structures and detecting complex correlations.
- L2 regularization, specifically with Lambda = 0.01, effectively reduced data complexity and dispersion, thereby preventing overfitting.
- Optimizing Lambda during training improved weight biases in Kohonen and MLP networks, leading to enhanced prediction accuracy.
Conclusions:
- The combination of PCA, SOM, and L2 regularization offers a robust strategy for meteorological modeling.
- L2 regularization is a key technique for improving the performance and accuracy of ANNs in predicting relative humidity.
- This integrated approach enhances the reliability of meteorological predictions by addressing overfitting and uncovering complex data patterns.
Related Concept Videos
01:11Residuals and Least-Squares Property
7.2K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
7.2K
01:20Calibration Curves: Linear Least Squares
1.1K
A calibration curve is a plot of the instrument's response against a series of known concentrations of a substance. This curve is used to set the instrument response levels, using the substance and its concentrations as standards. Alternatively, or additionally, an equation is fitted to the calibration curve plot and subsequently used to calculate the unknown concentrations of other samples reliably.
For data that follow a straight line, the standard method for fitting is the linear...
For data that follow a straight line, the standard method for fitting is the linear...
1.1K
01:52Regression Toward the Mean
6.2K
Regression toward the mean (“RTM”) is a phenomenon in which extremely high or low values—for example, and individual’s blood pressure at a particular moment—appear closer to a group’s average upon remeasuring. Although this statistical peculiarity is the result of random error and chance, it has been problematic across various medical, scientific, financial and psychological applications. In particular, RTM, if not taken into account, can interfere when...
6.2K
01:12Modeling and Similitude
123
Scaled modeling is a fundamental technique in engineering, enabling the study of large and complex systems by creating smaller, manageable replicas that recreate critical characteristics of the original. In hydrology and civil infrastructure, for example, scaled models of dams help analyze water flow, turbulence, and pressure. This method allows for accurate predictions of real-world behavior within a controlled environment, significantly reducing the cost and time involved in full-scale...
123
01:17Precipitation and Co-precipitation
1.6K
Precipitation and coprecipitation methods can be used to separate a mixture of ions in a solution. In qualitative inorganic analysis, ions that form sparingly soluble precipitates with the same reagent are separated based on the differences in solubility products. For example, consider the separation of Cu(II) and Fe(II) ions by precipitation as insoluble sulfides. First, copper(II) sulfide is precipitated by the addition of acidic H2S, where the dissociation of H2S is suppressed. Adding H2S...
1.6K
01:12Precipitation Processes
332
The experimental conditions in a gravimetric analysis should be optimized to maximize the particle size and purity of the obtained precipitate. Ideally, the concentration of the precipitating reagent should be low with effective stirring to maintain low relative supersaturation for the growth of large crystals. In homogeneous precipitation, the precipitant is slowly generated by a chemical reaction in the solution to avoid local reagent excesses. For example, urea decomposes gradually to...
332