The great potential of the convolutional neural networks (CNNs) provides novel and alternative ways to monitor important parameters with high accuracy. In this study, we developed a soft sensor model for dynamic processes based on a CNN for the measurement of suspended solids and turbidity from a single image of the liquid sample to be measured by using a commercial smartphone camera (Android or IOS system) and light-emitting diode (LED) illumination. For this, an image dataset of liquid samples illuminated with white, red, green, and blue LED light was taken and used to train a CNN and fit a multiple linear regression (MLR) by using different color lighting, we evaluated which color gives more accurate information about the concentration of suspended particles in the sample. We implemented a pre-trained AlexNet model, and an MLR to estimate total suspended solids (TSS), and turbidity values in liquid samples based on suspended particles. The proposed technique obtained high goodness of fit ($R^2$ = 0.99). The best performance was achieved using white light, with an accuracy of 98.24% and 97.20% for TSS and turbidity, respectively, with an operational range of 0–800 ${\mathrm{mgL}}^{-1}$, and 0–306 NTU. This system was designed for aquaculture environments and tested with both commercial fish feed and paprika. This motivates further research with different aquatic environments such as river water, domestic and industrial wastewater, and potable water, among others.

Advances in convolutional neural networks (CNNs) provide novel and alternative solutions for water quality management. This paper evaluates state-of-the-art optimization strategies available in PyTorch to date using AlexNet, a simple yet powerful CNN model. We assessed twelve optimization algorithms: Adadelta, Adagrad, Adam, AdamW, Adamax, ASGD, LBFGS, NAdam, RAdam, RMSprop, Rprop, and SGD under default conditions. The AlexNet model, pre-trained and coupled with a Multiple Linear Regression (MLR) model, was used to estimate the quantity black pixels (suspended solids) randomly distributed on a white background image, representing total suspended solids in liquid samples. Simulated images were used instead of real samples to maintain a controlled environment and eliminate variables that could introduce noise and optical aberrations, ensuring a more precise evaluation of the optimization algorithms. The performance of the CNN was evaluated using the accuracy, precision, recall, specificity, and F_Score metrics. Meanwhile, MLR was evaluated with the coefficient of determination ($R^2$), mean absolute and mean square errors. The results indicate that the top five optimizers are Adagrad, Rprop, Adamax, SGD, and ASGD, with accuracy rates of 100% for each optimizer, and $R^2$ values of 0.996, 0.959, 0.971, 0.966, and 0.966, respectively. Instead, the three worst performing optimizers were Adam, AdamW, and NAdam with accuracy rates of 22.2%, 11.1% and 11.1%, and $R^2$ values of 0.000, 0.148, and 0.000, respectively. These findings demonstrate the significant impact of optimization algorithms on CNN performance and provide valuable insights for selecting suitable optimizers to water quality assessment, filling existing gaps in the literature. This motivates further research to test the best optimizer models using real data to validate the findings and enhance their practical applicability, explaining how the optimizers can be used with real data.

In the last few years, Satellite Precipitation Estimates (SPE) have been increasingly used for rainfall estimation applications. Their validity and accuracy are influenced by several factors related to the location where the SPEs are applied. The objective of this study is to evaluate the performance of the Integrated Multisatellite Retrievals for Global Precipitation Measurement Version 06 Half-Hour Temporal Resolution (IMERG-FR V06 HH) for rainfall estimation, as well as to determine its relationships with the hourly and daily rain gauge network data in a semiarid region during 2019–2021. The methodology contemplates the temporality, elevation, rainfall intensity, and rain gauge density variables, carrying out a point-to-pixel analysis using continuous, (Bias, r, ME, and RMSE), categorical (POD, FAR, and CSI), and volumetric (VHI, VFAR, and VCSI) statistical metrics to understand the different behaviors between the rain gauge and IMERG-FR V06 HH data. IMERG-FR greatly underestimated the heavy rainfall events in values of −63.54 to −23.58 mm/day and −25.29 to −11.74 mm/30 min; however, it overestimates the frequency of moderate rain events (1 to 25 mm/day). At making the correlation (r) between the temporal scales, the monthly temporal resolution was the one that better relates the measured and estimated data, as well as reported r values of 0.83 and 0.85, where records at shorter durations in IMERG-FR do not detect them. The weakness of this system, according to the literature and confirmed by the research findings, in the case of hydrological phenomena, is that recording or estimating short durations is essential for the water project, and therefore, the placement of rain gauges. The 1902–2101 m.a.s.l. range elevation has the best behavior between the data with the lowest error and best detection ability, of which IMERG-FR tended to overestimate the rain at higher altitudes. Considering that the r for two automated rain gauges per IMERG-FR pixel density was 0.74, this indicates that the automated rain gauges versus IMERG-FR have a better data fit than the rain gauges versus IMERG-FR. The distance to centroid and climatic evaluations did not show distinctive differences in the performance of IMERG. These findings are useful to improve the IMERG-FR algorithms, guide users about its performance at semiarid plateau regions, and assist in the recording of data for hydrological projects.

In this work, a novel model of Markov Random Field (MRF) is introduced. Such a model is based on a proposed Semi-Huber potential function and it is applied successfully to image segmentation in presence of noise. The main difference with respect to other half-quadratic models that have been taken as a reference is, that the number of parameters to be tuned in the proposed model is smaller and simpler. The idea is then, to choose adequate parameter values heuristically for a good segmentation of the image. In that sense, some experimental results show that the proposed model allows an easier parameter adjustment with reasonable computation times.