The use of renewable energies is increasing around the world in order to deal with the environmental and economic problems related with conventional generation. In this sense, photovoltaic generation is one of the most promising technologies because of the high availability of sunlight, the easiness of maintenance, and the reduction in the costs of installation and production. However, photovoltaic panels are elements that must be located outside in order to receive the sun radiation and transform it into electricity. Therefore, they are exposed to the weather conditions and many environmental factors that can negatively affect the output delivered by the system. One of the most common issues related to the outside location is the dust accumulation in the surface of the panels. The dust particles obstruct the passage of the sunlight, reducing the efficiency of the generation process and making the system prone to experimental long-term faults. Thus, it is necessary to develop techniques that allow us to assess the level of dust accumulation in the panel surface in order to schedule a proper maintenance and avoid losses associated with the reduction of the delivered power and unexpected faults. In this work, we propose a methodology that uses a machine learning approach to estimate different levels of dust accumulation in photovoltaic panels. The developed method takes the voltage, current, temperature, and sun radiance as inputs to perform a statistical feature extraction that describes the behavior of the photovoltaic system under different dust conditions. In order to retain only the relevant information, a genetic algorithm works along with the principal component analysis technique to perform an optimal feature selection. Next, the linear discrimination analysis is carried out using the optimized dataset to reduce the problem dimensionality, and a multi-layer perceptron neural network is implemented as a classifier for discriminating among three different conditions: clean surface, slight dust accumulation, and severe dust accumulation. The proposed methodology is implemented using real signals from a photovoltaic installation, proving to be effective not only to determine if a dust accumulation condition is present but also when maintenance actions must be performed. Moreover, the results demonstrate that the accuracy of the proposed method is always above 94%.