Hyperspectral remote sensing has tremendous potential for monitoring land cover and water bodies from the rich spatial and spectral information contained in the images. It is a time and resource consuming task to obtain groundtruth data for these images by field sampling. A semi-supervised method for labeling and classification of hyperspectral images is presented. The unsupervised stage consists of image enhancement by feature extraction, followed by clustering for labeling and generating the groundtruth image. The supervised stage for classification consists of a preprocessing stage involving normalization, computation of principal components, and feature extraction. An ensemble of machine learning models takes the extracted features and groundtruth data from the unsupervised stage as input and a decision block then combines the output of the machines to label the image based on majority voting. The ensemble of machine learning methods includes support vector machines, gradient boosting, Gaussian classifier, and linear perceptron. Overall, the gradient boosting method gives the best performance for supervised classification of hyperspectral images. The presented ensemble method is useful for generating labeled data for hyperspectral images that do not have groundtruth information. It gives an overall accuracy of 93.74% for the Jasper hyperspectral image, 100% accuracy for the HSI2 Lake Erie images, and 99.92% for the classification of cyanobacteria or harmful algal blooms and surface scum. The method distinguishes well between blue green algae and surface scum. The full pipeline ensemble method for classifying Lake Erie images in a cloud server runs 24 times faster than a workstation.

This article presents a dataset for thermal characterization of photovoltaic systems to identify snail trails and hot spot failures. This dataset has 277 thermographic aerial images that were acquired by a Zenmuse XT IR camera (7-13 μ m wavelength) from a DJI Matrice 100 1drone (quadcopter). Additionally, our dataset includes the next environmental measurements: temperature, wind speed, and irradiance. The experimental set up consisted in a photovoltaic array of 4 serial monocrystalline Si panels (string) and an electronic equipment emulating a real load. The conditions for images acquisition were stablished in a flight protocol in which we defined altitude, attitude, and weather conditions.

Photovoltaic (PV) power generation forecasting is an important research topic, aiming to mitigate variability caused by weather conditions and improve power generation planning. Climate factors, including solar irradiance, temperature, and cloud cover, influence the energy conversion achieved by PV systems. Long-term weather forecasting improves PV power generation planning, while short-term forecasting enhances control methods, such as managing ramp rates. The stochastic nature of weather variables poses a challenge for linear regression methods. Consequently, advanced, state-of-the-art machine learning (ML) approaches capable of handling non-linear data, such as long short-term memory (LSTM), have emerged. This paper introduces the implementation of a multivariate machine learning model to forecast PV power generation, considering multiple weather variables. A deep learning solution was implemented to analyze weather variables in a short time horizon. Utilizing a hidden Markov model for data preprocessing, an LSTM model was trained using the Alice Spring dataset provided by DKA Solar Center. The proposed workflow demonstrated superior performance compared to the results obtained by state-of-the-art methods, including support vector machine, radiation classification coordinate with LSTM (RCC-LSTM), and ESNCNN specifically concerning the proposed multi-input single-output LSTM model. This improvement is attributed to incorporating input features such as active power, temperature, humidity, horizontal and diffuse irradiance, and wind direction, with active power serving as the output variable. The proposed workflow achieved a mean square error (MSE) of 2.17×10-7, a root mean square error (RMSE) of 4.65×10-4, and a mean absolute error (MAE) of 4.04×10-4.

Harmful algal blooms have dangerous repercussions for biodiversity, the ecosystem, and public health. Automatic identification based on remote sensing hyperspectral image analysis provides a valuable mechanism for extracting the spectral signatures of harmful algal blooms and their respective percentage in a region of interest. This paper proposes a new model called a non-symmetrical autoencoder for spectral unmixing to perform endmember extraction and fractional abundance estimation. The model is assessed in benchmark datasets, such as Jasper Ridge and Samson. Additionally, a case study of the HSI2 image acquired by NASA over Lake Erie in 2017 is conducted for extracting optical water types. The results using the proposed model for the benchmark datasets improve unmixing performance, as indicated by the spectral angle distance compared to five baseline algorithms. Improved results were obtained for various metrics. In the Samson dataset, the proposed model outperformed other methods for water (0.060) and soil (0.025) endmember extraction. Moreover, the proposed method exhibited superior performance in terms of mean spectral angle distance compared to the other five baseline algorithms. The non-symmetrical autoencoder for the spectral unmixing approach achieved better results for abundance map estimation, with a root mean square error of 0.091 for water and 0.187 for soil, compared to the ground truth. For the Jasper Ridge dataset, the non-symmetrical autoencoder for the spectral unmixing model excelled in the tree (0.039) and road (0.068) endmember extraction and also demonstrated improved results for water abundance maps (0.1121). The proposed model can identify the presence of chlorophyll-a in waterbodies. Chlorophyll-a is an essential indicator of the presence of the different concentrations of macrophytes and cyanobacteria. The non-symmetrical autoencoder for spectral unmixing achieves a value of 0.307 for the spectral angle distance metric compared to a reference ground truth spectral signature of chlorophyll-a. The source code for the proposed model, as implemented in this manuscript, can be found at https://github.com/EstefaniaAlfaro/autoencoder_owt_spectral.git.

Graph convolutional neural network architectures combine feature extraction and convolutional layers for hyperspectral image classification. An adaptive neighborhood aggregation method based on statistical variance integrating the spatial information along with the spectral signature of the pixels is proposed for improving graph convolutional network classification of hyperspectral images. The spatial-spectral information is integrated into the adjacency matrix and processed by a single-layer graph convolutional network. The algorithm employs an adaptive neighborhood selection criteria conditioned by the class it belongs to. Compared to fixed window-based feature extraction, this method proves effective in capturing the spectral and spatial features with variable pixel neighborhood sizes. The experimental results from the Indian Pines, Houston University, and Botswana Hyperion hyperspectral image datasets show that the proposed AN-GCN can significantly improve classification accuracy. For example, the overall accuracy for Houston University data increases from 81.71% (MiniGCN) to 97.88% (AN-GCN). Furthermore, the AN-GCN can classify hyperspectral images of rice seeds exposed to high day and night temperatures, proving its efficacy in discriminating the seeds under increased ambient temperature treatments.