Very short-term reactive forecasting of the solar ultraviolet index using an extreme learning machine integrated with the solar zenith angle

Enhanced joint hybrid deep neural network explainable artificial intelligence model for 1-hr ahead solar ultraviolet index prediction

BACKGROUND AND OBJECTIVE

Exposure to solar ultraviolet (UV) radiation can cause malignant keratinocyte cancer and eye disease. Developing a user-friendly, portable, real-time solar UV alert system especially or wearable electronic mobile devices can help reduce the exposure to UV as a key measure for personal and occupational management of the UV risks. This research aims to design artificial intelligence-inspired early warning tool tailored for short-term forecasting of UV index (UVI) integrating satellite-derived and ground-based predictors for Australian hotspots receiving high UV exposures. The study further improves the trustworthiness of the newly designed tool using an explainable artificial intelligence approach.

METHODS

An enhanced joint hybrid explainable deep neural network model (called EJH-X-DNN) is constructed involving two phases of feature selection and hyperparameter tuning using Bayesian optimization. A comprehensive assessment of EJH-X- DNN is conducted with six other competing benchmarked models. The proposed model is explained locally and globally using robust model-agnostic explainable artificial intelligence frameworks such as Local Interpretable Model-Agnostic Explanations (LIME), Shapley additive explanations (SHAP), and permutation feature importance (PFI).

RESULTS

The newly proposed model outperformed all benchmarked models for forecasting hourly horizons UVI, with correlation coefficients of 0.900, 0.960, 0.897, and 0.913, respectively, for Darwin, Alice Springs, Townsville, and Emerald hotspots. According to the combined local and global explainable model outcomes, the site-based results indicate that antecedent lagged memory of UVI and solar zenith angle are influential features. Predictions made by EJH-X-DNN model are strongly influenced by factors such as ozone effect, cloud conditions, and precipitation.

CONCLUSION

With its superiority and skillful interpretation, the UVI prediction system reaffirms its benefits for providing real-time UV alerts to mitigate risks of skin and eye health complications, reducing healthcare costs and contributing to outdoor exposure policy.

Forecasting of solar radiation for a cleaner environment using robust machine learning techniques

Intensified research is going on worldwide to increase renewable energy sources like solar and wind to reduce emissions and achieve worldwide targets and also to address the depleting fossil fuels resources and meet the increasing energy demand of the population. Solar radiation (SR) is intermittent, so forecasting solar radiation is a must. The objective of this research is to use modern machine techniques for different climatic conditions to forecast SR with higher accuracy. The required dataset is collected from National Solar Radiation Database having features such as temperature, pressure, relative humidity, dew point, solar zenith angle, wind speed, and direction, concerning the y-parameter Global Horizontal Irradiance (GHI) (W/m²). The collected data is first split based on different types of climatic conditions. Each climatic model was trained on various machine learning (ML) algorithms like multiple linear regression (MLR), support vector regression (SVR), decision tree regression (DTR), random forest regression (RFR), gradient boosting regression (GBR), lasso and ridge regression, and deep learning algorithm especially long-short-term memory (LSTM) using Google Colab Platform. From the analysis, LSTM has the least error approximation of 0.0040 loss at the 100^th epoch and of all ML models, gradient boosting and RFR top high, when it comes to the Hot weather season-gradient boosting leads 2% than RFR, and similarly for cold weather, autumn and monsoon climate-RFR has 1% higher accuracy than gradient boosting. This high-accuracy model is deployed in a user interface (UI) that will be more useful for real-time solar prediction, load operators for maintenance scheduling, stock commitment, and load dispatch centres for engineers to decide on setting up solar panels, for household clients and future researchers.

The development of dissolved oxygen forecast model using hybrid machine learning algorithm with hydro-meteorological variables

Dissolved oxygen (DO) forecasting is essential for aquatic managers responsible for maintaining ecosystem health and the management of water bodies affected by water quality parameters. This paper aims to forecast dissolved oxygen (DO) concentration using a multivariate adaptive regression spline (MARS) hybrid model coupled with maximum overlap discrete wavelet transformation (MODWT) as a feature decomposition approach for Surma River water using a set of water quality hydro-meteorological variables. The proposed hybrid model is compared with numerous machine learning methods, namely Bayesian ridge regression (BNR), k-nearest neighbourhood (KNN), kernel ridge regression (KRR), random forest (RF), and support vector regression (SVR). The investigational results show that the proposed model of MODWT-MARS has a better prediction than the comparing benchmark models and individual standalone counter parts. The result shows that the hybrid algorithms (i.e. MODWT-MARS) outperformed the other models (r = 0.981, WI = 0.990, RMAE = 2.47%, and MAE = 0.089). This hybrid method may serve to forecast water quality variables with fewer predictor variables.

Machine learning in the identification, prediction and exploration of environmental toxicology: Challenges and perspectives

Over the past few decades, data-driven machine learning (ML) has distinguished itself from hypothesis-driven studies and has recently received much attention in environmental toxicology. However, the use of ML in environmental toxicology remains in the early stages, with knowledge gaps, technical bottlenecks in data quality, high-dimensional/heterogeneous/small-sample data analysis and model interpretability, and a lack of an in-depth understanding of environmental toxicology. Given the above problems, we review the recent progress in the literature and highlight state-of-the-art toxicological studies using ML (such as learning and predicting toxicity in complicated biosystems and multiple-factor environmental scenarios of long-term and large-scale pollution). Beyond predicting simple biological endpoints by integrating untargeted omics and adverse outcome pathways, ML development should focus on revealing toxicological mechanisms. The integration of data-driven ML with other methods (e.g., omics analysis and adverse outcome pathway frameworks) endows ML with widely promising application in revealing toxicological mechanisms. High-quality databases and interpretable algorithms are urgently needed for toxicology and environmental science. Addressing the core issues and future challenges for ML in this review may narrow the knowledge gap between environmental toxicity and computational science and facilitate the control of environmental risk in the future.

An Hour-Ahead PV Power Forecasting Method Based on an RNN-LSTM Model for Three Different PV Plants

Incorporating solar energy into a grid necessitates an accurate power production forecast for photovoltaic (PV) facilities. In this research, output PV power was predicted at an hour ahead on yearly basis for three different PV plants based on polycrystalline (p-si), monocrystalline (m-si), and thin-film (a-si) technologies over a four-year period. Wind speed, module temperature, ambiance, and solar irradiation were among the input characteristics taken into account. Each PV plant power output was the output parameter. A deep learning method (RNN-LSTM) was developed and evaluated against existing techniques to forecast the PV output power of the selected PV plant. The proposed technique was compared with regression (GPR, GPR (PCA)), hybrid ANFIS (grid partitioning, subtractive clustering and FCM) and machine learning (ANN, SVR, SVR (PCA)) methods. Furthermore, different LSTM structures were also investigated, with recurrent neural networks (RNN) based on 2019 data to determine the best structure. The following parameters of prediction accuracy measure were considered: RMSE, MSE, MAE, correlation (r) and determination (R2) coefficients. In comparison to all other approaches, RNN-LSTM had higher prediction accuracy on the basis of minimum (RMSE and MSE) and maximum (r and R2). The p-si, m-si and a-si PV plants showed the lowest RMSE values of 26.85 W/m2, 19.78 W/m2 and 39.2 W/m2 respectively. Moreover, the proposed method was found to be robust and flexible in forecasting the output power of the three considered different photovoltaic plants.

Optimization algorithms as training approach with hybrid deep learning methods to develop an ultraviolet index forecasting model

The solar ultraviolet index (UVI) is a key public health indicator to mitigate the ultraviolet-exposure related diseases. This study aimed to develop and compare the performances of different hybridised deep learning approaches with a convolutional neural network and long short-term memory referred to as CLSTM to forecast the daily UVI of Perth station, Western Australia. A complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is incorporated coupled with four feature selection algorithms (i.e., genetic algorithm (GA), ant colony optimization (ACO), particle swarm optimization (PSO), and differential evolution (DEV)) to understand the diverse combinations of the predictor variables acquired from three distinct datasets (i.e., satellite data, ground-based SILO data, and synoptic mode climate indices). The CEEMDAN-CLSTM model coupled with GA appeared to be an accurate forecasting system in capturing the UVI. Compared to the counterpart benchmark models, the results demonstrated the excellent forecasting capability (i.e., low error and high efficiency) of the recommended hybrid CEEMDAN-CLSTM model in apprehending the complex and non-linear relationships between predictor variables and the daily UVI. The study inference can considerably enhance real-time exposure advice for the public and help mitigate the potential for solar UV-exposure-related diseases such as melanoma.

A Data-Driven Method for the Temporal Estimation of Soil Water Potential and Its Application for Shallow Landslides Prediction

Soil water potential is a key factor to study water dynamics in soil and for estimating the occurrence of natural hazards, as landslides. This parameter can be measured in field or estimated through physically-based models, limited by the availability of effective input soil properties and preliminary calibrations. Data-driven models, based on machine learning techniques, could overcome these gaps. The aim of this paper is then to develop an innovative machine learning methodology to assess soil water potential trends and to implement them in models to predict shallow landslides. Monitoring data since 2012 from test-sites slopes in Oltrepò Pavese (northern Italy) were used to build the models. Within the tested techniques, Random Forest models allowed an outstanding reconstruction of measured soil water potential temporal trends. Each model is sensitive to meteorological and hydrological characteristics according to soil depths and features. Reliability of the proposed models was confirmed by correct estimation of days when shallow landslides were triggered in the study areas in December 2020, after implementing the modeled trends on a slope stability model, and by the correct choice of physically-based rainfall thresholds. These results confirm the potential application of the developed methodology to estimate hydrological scenarios that could be used for decision-making purposes.

Accurate surface ultraviolet radiation forecasting for clinical applications with deep neural network

Exposure to appropriate doses of UV radiation provides enormously health and medical treatment benefits including psoriasis. Typical hospital-based phototherapy cabinets contain a bunch of artificial lamps, either broad-band (main emission spectrum 280-360 nm, maximum 320 nm), or narrow-band UV B irradiation (main emission spectrum 310-315 nm, maximum 311 nm). For patients who cannot access phototherapy centers, sunbathing, or heliotherapy, can be a safe and effective treatment alternative. However, as sunlight contains the full range of UV radiation (290-400 nm), careful sunbathing supervised by photodermatologist based on accurate UV radiation forecast is vital to minimize potential adverse effects. Here, using 10-year UV radiation data collected at Nakhon Pathom, Thailand, we developed a deep learning model for UV radiation prediction which achieves around 10% error for 24-h forecast and 13-16% error for 7-day up to 4-week forecast. Our approach can be extended to UV data from different geographical regions as well as various biological action spectra. This will become one of the key tools for developing national heliotherapy protocol in Thailand. Our model has been made available at https://github.com/cmb-chula/SurfUVNet .

Deep Learning Forecasts of Soil Moisture: Convolutional Neural Network and Gated Recurrent Unit Models Coupled with Satellite-Derived MODIS, Observations and Synoptic-Scale Climate Index Data

Remotely sensed soil moisture forecasting through satellite-based sensors to estimate the future state of the underlying soils plays a critical role in planning and managing water resources and sustainable agricultural practices. In this paper, Deep Learning (DL) hybrid models (i.e., CEEMDAN-CNN-GRU) are designed for daily time-step surface soil moisture (SSM) forecasts, employing the gated recurrent unit (GRU), complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), and convolutional neural network (CNN). To establish the objective model’s viability for SSM forecasting at multi-step daily horizons, the hybrid CEEMDAN-CNN-GRU model is tested at 1st, 5th, 7th, 14th, 21st, and 30th day ahead period by assimilating a comprehensive pool of 52 predictor dataset obtained from three distinct data sources. Data comprise satellite-derived Global Land Data Assimilation System (GLDAS) repository a global, high-temporal resolution, unique terrestrial modelling system, and ground-based variables from Scientific Information Landowners (SILO) and synoptic-scale climate indices. The results demonstrate the forecasting capability of the hybrid CEEMDAN-CNN-GRU model with respect to the counterpart comparative models. This is supported by a relatively lower value of the mean absolute percentage and root mean square error. In terms of the statistical score metrics and infographics employed to test the final model’s utility, the proposed CEEMDAN-CNN-GRU models are considerably superior compared to a standalone and other hybrid method tested on independent SSM data developed through feature selection approaches. Thus, the proposed approach can be successfully implemented in hydrology and agriculture management.

Prediction of Potential Evapotranspiration Using Temperature-Based Heuristic Approaches

The potential or reference evapotranspiration (ET0) is considered as one of the fundamental variables for irrigation management, agricultural planning, and modeling different hydrological pr°Cesses, and therefore, its accurate prediction is highly essential. The study validates the feasibility of new temperature based heuristic models (i.e., group method of data handling neural network (GMDHNN), multivariate adaptive regression spline (MARS), and M5 model tree (M5Tree)) for estimating monthly ET0. The outcomes of the newly developed models are compared with empirical formulations including Hargreaves-Samani (HS), calibrated HS, and Stephens-Stewart (SS) models based on mean absolute error (MAE), root mean square error (RMSE), and Nash-Sutcliffe efficiency. Monthly maximum and minimum temperatures (Tmax and Tmin) observed at two stations in Turkey are utilized as inputs for model development. In the applications, three data division scenarios are utilized and the effect of periodicity component (PC) on models’ accuracies are also examined. By importing PC into the model inputs, the RMSE accuracy of GMDHNN, MARS, and M5Tree models increased by 1.4%, 8%, and 6% in one station, respectively. The GMDHNN model with periodic input provides a superior performance to the other alternatives in both stations. The recommended model reduced the average error of MARS, M5Tree, HS, CHS, and SS models with respect to RMSE by 3.7–6.4%, 10.7–3.9%, 76–75%, 10–35%, and 0.8–17% in estimating monthly ET0, respectively. The HS model provides the worst accuracy while the calibrated version significantly improves its accuracy. The GMDHNN, MARS, M5Tree, SS, and CHS models are also compared in estimating monthly mean ET0. The GMDHNN generally gave the best accuracy while the CHS provides considerably over/under-estimations. The study indicated that the only one data splitting scenario may mislead the modeler and for better validation of the heuristic methods, more data splitting scenarios should be applied.

Dissolved oxygen prediction using a new ensemble method

Prediction of dissolved oxygen which is an important water quality (WQ) parameter is crucial for aquatic managers who have responsibility for the ecosystem health's maintenance and for the management of reservoirs related to WQ. This study proposes a new ensemble method, Bayesian model averaging (BMA), for estimating hourly dissolved oxygen. The potential of the BMA was investigated and compared with five data-driven methods, extreme leaning machine (ELM), artificial neural networks (ANNs), adaptive neuro-fuzzy inference system (ANFIS), classification and regression tree (CART), and multilinear regression (MLR), by considering hourly temperature, pH, and specific conductivity data as inputs. The methods were compared with respect to three statistics, root mean square errors (RMSE), Nash-Sutcliffe efficiency, and determination coefficient. Results based on two stations' data indicated that the proposed method performed superior to the ELM, ANN, ANFIS, CART, and MLR in estimation of hourly dissolved oxygen; corresponding improvements obtained by BMA are about 5-8%, 13-12%, 7-9%, and 18-27% with respect to RMSE. The ELM also outperformed the other four methods (ANN, ANFIS, CART, and MLR), and the CART and MLR indicated the lowest estimation accuracy in both stations. Examination of various input combinations revealed that the most effective variable is water temperature while the specific conductivity has negligible effect on hourly dissolved oxygen.

Redefining the Use of Big Data in Urban Health for Increased Liveability in Smart Cities

Policy decisions and urban governance are being influenced by an emergence of data from internet of things (IoT), which forms the backbone of Smart Cities, giving rise to Big Data which is processed and analyzed by Artificial Intelligence models at speeds unknown to mankind decades ago. This is providing new ways of understanding how well cities perform, both in terms of economics as well as in health. However, even though cities have been increasingly digitalized, accelerated by the concept of Smart Cities, the exploration of urban health has been limited by the interpretation of sensor data from IoT devices, omitting the inclusion of data from human anatomy and the emergence of biological data in various forms. This paper advances the need for expanding the concept of Big Data beyond infrastructure to include that of urban health through human anatomy; thus, providing a more cohesive set of data, which can lead to a better knowledge as to the relationship of people with the city and how this pertains to the thematic of urban health. Coupling both data forms will be key in supplementing the contemporary notion of Big Data for the pursuit of more contextualized, resilient, and sustainable Smart Cities, rendering more liveable fabrics, as outlined in the Sustainable Development Goal (SDG) 11 and the New Urban Agenda.

Design and implementation of a hybrid model based on two-layer decomposition method coupled with extreme learning machines to support real-time environmental monitoring of water quality parameters

Accurate prediction of water quality parameters plays a crucial and decisive role in environmental monitoring, ecological systems sustainability, human health, aquaculture and improved agricultural practices. In this study a new hybrid two-layer decomposition model based on the complete ensemble empirical mode decomposition algorithm with adaptive noise (CEEMDAN) and the variational mode decomposition (VMD) algorithm coupled with extreme learning machines (ELM) and also least square support vector machine (LSSVM) was designed to support real-time environmental monitoring of water quality parameters, i.e. chlorophyll-a (Chl-a) and dissolved oxygen (DO) in a Lake reservoir. Daily measurements of Chl-a and DO for June 2012-May 2013 were employed where the partial autocorrelation function was applied to screen the relevant inputs for the model construction. The variables were then split into training, validation and testing subsets where the first stage of the model testing captured the superiority of the ELM over the LSSVM algorithm. To improve these standalone predictive models, a second stage implemented a two-layer decomposition with the model inputs decomposed in the form of high and low frequency oscillations, represented by the intrinsic mode function (IMF) through the CEEMDAN algorithm. The highest frequency component, IMF1 was further decomposed with the VMD algorithm to segregate key model input features, leading to a two-layer hybrid VMD-CEEMDAN model. The VMD-CEEMDAN-ELM model was able to reduce the root mean square and the mean absolute error by about 14.04% and 7.12% for the Chl-a estimation and about 5.33% and 4.30% for the DO estimation, respectively, compared with the standalone counterparts. Overall, the developed methodology demonstrates the robustness of the two-phase VMD-CEEMDAN-ELM model in identifying and analyzing critical water quality parameters with a limited set of model construction data over daily horizons, and thus, to actively support environmental monitoring tasks, especially in case of high-frequency, and relatively complex, real-time datasets.

Mapping groundwater contamination risk of multiple aquifers using multi-model ensemble of machine learning algorithms

Constructing accurate and reliable groundwater risk maps provide scientifically prudent and strategic measures for the protection and management of groundwater. The objectives of this paper are to design and validate machine learning based-risk maps using ensemble-based modelling with an integrative approach. We employ the extreme learning machines (ELM), multivariate regression splines (MARS), M5 Tree and support vector regression (SVR) applied in multiple aquifer systems (e.g. unconfined, semi-confined and confined) in the Marand plain, North West Iran, to encapsulate the merits of individual learning algorithms in a final committee-based ANN model. The DRASTIC Vulnerability Index (VI) ranged from 56.7 to 128.1, categorized with no risk, low and moderate vulnerability thresholds. The correlation coefficient (r) and Willmott's Index (d) between NO₃ concentrations and VI were 0.64 and 0.314, respectively. To introduce improvements in the original DRASTIC method, the vulnerability indices were adjusted by NO₃ concentrations, termed as the groundwater contamination risk (GCR). Seven DRASTIC parameters utilized as the model inputs and GCR values utilized as the outputs of individual machine learning models were served in the fully optimized committee-based ANN-predictive model. The correlation indicators demonstrated that the ELM and SVR models outperformed the MARS and M5 Tree models, by virtue of a larger d and r value. Subsequently, the r and d metrics for the ANN-committee based multi-model in the testing phase were 0.8889 and 0.7913, respectively; revealing the superiority of the integrated (or ensemble) machine learning models when compared with the original DRASTIC approach. The newly designed multi-model ensemble-based approach can be considered as a pragmatic step for mapping groundwater contamination risks of multiple aquifer systems with multi-model techniques, yielding the high accuracy of the ANN committee-based model.

The geospatial relationship of pterygium and senile cataract with ambient solar ultraviolet in tropical Ecuador

The distribution of modelled surface ultraviolet for Ecuador, South America was determined by satellite observation and compared to national pterygium (WHO ICD H11) and senile cataract (WHO ICD H25) incidence.

Forecasting of groundwater level fluctuations using ensemble hybrid multi-wavelet neural network-based models

Accurate prediction of groundwater level (GWL) fluctuations can play an important role in water resources management. The aims of the research are to evaluate the performance of different hybrid wavelet-group method of data handling (WA-GMDH) and wavelet-extreme learning machine (WA-ELM) models and to combine different wavelet based models for forecasting the GWL for one, two and three months step-ahead in the Maragheh-Bonab plain, NW Iran, as a case study. The research used totally 367 monthly GWLs (m) datasets (Sep 1985-Mar 2016) which were split into two subsets; the first 312 datasets (85% of total) were used for model development (training) and the remaining 55 ones (15% of total) for model evaluation (testing). The stepwise selection was used to select appropriate lag times as the inputs of the proposed models. The performance criteria such as coefficient of determination (R²), root mean square error (RMSE) and Nash-Sutcliffe efficiency coefficient (NSC) were used for assessing the efficiency of the models. The results indicated that the ELM models outperformed GMDH models. To construct the hybrid wavelet based models, the inputs and outputs were decomposed into sub-time series employing different maximal overlap discrete wavelet transform (MODWT) functions, namely Daubechies, Symlet, Haar and Dmeyer of different orders at level two. Subsequently, these sub-time series were served in the GMDH and ELM models as an input dataset to forecast the multi-step-ahead GWL. The wavelet based models improved the performances of GMDH and ELM models for multi-step-ahead GWL forecasting. To combine the advantages of different wavelets, a least squares boosting (LSBoost) algorithm was applied. The use of the boosting multi-WA-neural network models provided the best performances for GWL forecasts in comparison with single WA-neural network-based models.