Environmental Time Series Data Research Articles

A nonparametrically corrected likelihood for Bayesian spectral analysis of multivariate time series

A novel approach to Bayesian nonparametric spectral analysis of stationary multivariate time series is presented. Starting with a parametric vector-autoregressive model, the parametric likelihood is nonparametrically adjusted in the frequency domain to account for potential deviations from parametric assumptions. A proof of mutual contiguity of the nonparametrically corrected likelihood, the multivariate Whittle likelihood approximation and the exact likelihood for Gaussian time series is given. A multivariate extension of the nonparametric Bernstein-Dirichlet process prior for univariate spectral densities to the space of Hermitian positive definite spectral density matrices is specified directly on the correction matrices. An infinite series representation of this prior is then used to develop a Markov chain Monte Carlo algorithm to sample from the posterior distribution. The code is made publicly available for ease of use and reproducibility. With this novel approach, a generalisation of the multivariate Whittle-likelihood-based method of Meier et al. (2020) as well as an extension of the nonparametrically corrected likelihood for univariate stationary time series of Kirch et al. (2019) to the multivariate case is presented. It is demonstrated that the nonparametrically corrected likelihood combines the efficiencies of a parametric with the robustness of a nonparametric model. Its numerical accuracy is illustrated in a comprehensive simulation study. Its practical advantages are illustrated by a spectral analysis of two environmental time series data sets: a bivariate time series of the Southern Oscillation Index and fish recruitment and a multivariate time series of windspeed data at six locations in California.

Determination Procedure of Ecotoxicologically Acceptable Cu Concentration in River Considering the Change of Environmental Factors

Objectives : In this study, considering the changes in the concentration of metal/metalloid and environmental factors over time of the target water system and the toxic effects of metals on various aquatic organisms, determined procedure of ecotoxicologically acceptable metal/metalloid concentration based on a biotic ligand model (BLM) was proposed in detail. As an application example, the ecotoxicologically acceptable Cu concentration for the Numedalslågen river in Norway was calculated.Methods : The Cu concentration and environmental factor time series data of the target water system were collected, and EC50[Cu]<sub>T</sub>, the total concentration of Cu in the water system showing a toxic effect of 50% on the target aquatic organisms, was calculated through BLM. In addition, the predicted no-effect concentration (PNEC) was obtained from the species sensitivity distribution using the acute-chronic ratio and adjustment factor, and the ecotoxicologically acceptable Cu concentration of the target water system was determined through the fixed monitoring benchmark (FMB).Results and Discussion : Ecotoxicologically acceptable Cu concentration of the target water system was determined as 1.15 μg/L. Dissolved organic carbon (DOC) showed the highest linear relationship with EC50[Cu]<sub>T</sub> (R<sup>2</sup> = 0.94-0.98) compared to various environmental factors, and the Cu toxicity effect on aquatic organisms tended to decrease as the DOC concentration increased. Ca showed a low linear relationship with EC50[Cu]<sub>T</sub> (R<sup>2</sup> < 0.04), which is presumed to be due to the decrease in Ca<sup>2+</sup> concentration due to the complexese formation of DOC and Ca<sup>2+</sup>, which reduced the competitive effect with Cu<sup>2+</sup>.Conclusion : The proposed procedure provides a useful method for calculating ecotoxicologically acceptable metal concentrations for the protection of aquatic organisms in water systems. In addition, it is expected that it can be used to calculate site-specific metal concentrations that can protect aquatic organisms in the target water system by reflecting the timing of sediment resuspension, which can cause rapid changes in the concentration of metals and environmental factors in the water system, and specific time points such as storm and flood seasons.

Application of ANN for coastal water quality prediction: Quang Binh case study

The coastal areas of Quang Binh province play a crucial role not only in the economic and tourism development of the coastal province but also in the overall development of the Northern Central region. Therefore, monitoring and forecasting seawater quality in this region is vital. However, the water quality condition assessment faces many limitations due to the lack of measured data and the complication of numerical models. Meanwhile, the artificial intelligence model for simulating and predicting water quality has been widely applied due to its timely and reliable calculating abilities. This research has piloted the prediction of some water pollution parameters on the coast of Quang Binh province using an artificial neural network (ANN) model. This presents a novel approach to identifying implicit relationships between variables based on data analysis techniques via ANN. An ANN model was built to analyze the measured environmental time series data at Dong Hoi station, Quang Binh province, from 2002 to 2022. The calculation results of the training (70% of the data set, NSE: 0.81) and testing (the rest 30% of the data set, NSE: 0.5) of the model have satisfied the total coliform parameter, indicating the promise of applying the ANN model for water quality prediction.

A statistical examination of the link between environmental performance and legal practices: an evaluation of China’s strategies for residual legislative power allocation

This study investigates the correlation between the environmental legal practices of different countries and their environmental performance. It entails an empirical analysis of cross-sectional environmental data collected from 34 countries, including members of the Organization for Economic Cooperation and Development (OECD) and the BRICs nations (Brazil, Russia, India, China, and South Africa). Then the study explores the correlation between a country’s environmental performance and both the environmental policy stringency and regulatory enforcement. The findings from this global assessment are subsequently corroborated through an examination of China’s environmental time series data spanning a decade, revealing a significant relationship between a country’s environmental performance and regulatory enforcement. These results validate the Incomplete Law Theory within the field of environmental law. Moreover, as the second most populous and the third-largest country in terms of land area globally, China’s environmental protection strategies and performance play a pivotal role in influencing international environmental outcomes. Consequently, the study conducts a case study on China’s environmental legal practices and provides suggestions for enhancing China’s allocation strategies of residual legislative power. The study advocates for the optimization of residual legislative power allocation within local environmental law enforcement agencies and a balanced distribution of public and private residual legislative power. This approach reinforces the government’s role in strategic formulation.

Personal comfort models in long-term monitoring using physiological data from wearable sensors

Personal Comfort Models (PCMs) propose a new approach for human-centric comfort studies overcoming the one-size-fits-all of the conventional models. This research addresses the development of PCMs based on a seven-month long-term monitoring campaign including continuous environmental and physiological data collection through wearables and daily survey submission about subjects’ sensations. To tackle the influence of subjects’ environmental exposure history, time series of environmental data of different durations were used to predict individuals’ perception via Machine Learning models with Support Vector Machine and Random Forest methods. The accuracy and F1-score values of seven different PCMs were confronted for each subject and for the whole group (nine people). The number of datapoints per subject and their answers’ consistency during time affected the models’ accuracy, and the inclusion of physiological signals improved the models’ performance. When considering the whole dataset, the comfort model accuracy decreases supporting that individual subjectivity have an important impact in the environmental perception prediction.

Density forecasting of conjunctivitis burden using high-dimensional environmental time series data

As one of the most common eye conditions being presented at clinics, acute conjunctivitis puts substantial strain on primary health resources. To reduce this public health burden, it is important to forecast and provide forward guidance to policymakers by estimating conjunctivitis trends, taking into account factors which influence transmission. Using a high-dimensional set of ambient air pollution and meteorological data, this study describes new approaches to point and probabilistic forecasting of conjunctivitis burden which can be readily translated to other infectious diseases. Over the period of 2012 – 2022, we show that simple models without environmental data provided better point forecasts but the more complex models which optimized predictive accuracy and combined multiple predictors demonstrated superior density forecast performance. These results were shown to be consistent over periods with and without structural breaks in transmission. Furthermore, ecological analysis using post-selection inference showed that increases in SO2, O3 surface concentration and total precipitation were associated to increased conjunctivitis attendance. The methods proposed can provide rich and informative forward guidance for outbreak preparedness and help guide healthcare resource planning in both stable periods of transmission and periods where structural breaks in data occur.

Predicting renewable energy production by machine learning methods: The case of Turkey

AbstractIt is considered that the use of renewable energy sources will replace fossil fuels due to global climate change and accompanying decisions taken by states. In this study, unlike the renewable energy production estimation studies in the literature, a model was created by taking the socioeconomic, environmental and energy time series data of the countries. In the study, Turkey, which did not promise a numerical reduction in greenhouse gas emissions unlike other developing countries but has an increasing energy production from renewable energy sources, was chosen. In the study, the data between 1990 and 2020 were used to receive more realistic results by considering the interval before and after the Kyoto protocol. Artificial neural networks and support vector regression among machine learning methods were used to predict the model. As a result of the study, support vector regression had a 92% and artificial neural networks had a successful predictive power of 89.9% according to the coefficient of determination (R2). In the study, the root mean square error value was 0.071 for artificial neural networks and 0.045 for support vector regression; the mean squared error value was 0.005 for artificial neural networks and 0.002 for support vector regression, which was close to the ideal values. Both methods were statistically successful. It is predicted that the model designed because of these successful results obtained in the study would guide the creation of energy policies and contribute to scientific studies.

Personalized Spiking Neural Network Models of Clinical and Environmental Factors to Predict Stroke

The high incidence of stroke occurrence necessitates the understanding of its causes and possible ways for early prediction and prevention. In this respect, statistical methods offer the “big picture,” but they have a weak predictive ability at an individual level. This research proposes a new personalized modeling method based on computational spiking neural networks (SNN) for the identification of causal associations between clinical and environmental time series data that can be used to predict individual stroke events. The method is tested on 804 stroke patients. Given a clinical data set of patients who experienced a stroke in the past and the corresponding environmental time-series data for a selected time-window before the stroke event, the method identifies the clusters of individuals with a high risk for stroke under similar conditions. The methodology involves a pipeline of processes when creating a personalized model for an individual x: (1) selecting a group of individuals Gx with similar personal records to x; (2) training a personalized SNN x model of several days of environmental data related to the Gx group to predict the risk of stroke for x at least one day earlier; (3) model interpretability through 3D visualization; (4) discovery of personalized predictive markers. The results are twofold, first proposing a new computational methodology and second presenting new findings. It is found that certain environmental factors, such as SO2, PM10, CO, and PM2.5, increase the risk of stroke if an individual x belongs to a certain cluster of people, characterized by a combination of family history of stroke and diabetes, overweight, vascular/heart disease, age, and other. For the used population data, the proposed method can predict accurately individual risk of stroke before the day of the stroke. The paper presents a new methodology for personalized machine learning methods to define subgroups of the population with a high risk of stroke and to predict early individual risk of the stroke event. This makes the proposed cognitive computation method useful to reduce morbidity and mortality in society. The method is broadly applicable for predicting individual risk of other diseases and mental health conditions.

An R package for identification of outliers in environmental time series data

Environmental data often include outliers that may significantly affect further modelling and data analysis. Although a number of outlier detection methods have been proposed, their use is usually complicated by the assumption of the distribution or model of the analyzed data. However, environmental variables are quite often influenced by many different factors and their distribution is difficult to estimate. The envoutliers package has been developed to provide users with a choice of recently presented, semi-parametric outlier detection methods that do not impose requirements on the distribution of the original data. This paper briefly describes the methodology as well as its implementation in the package. The application is illustrated on real data examples.

The associations between mental health and environmental factors in New Zealand: A region-based analytical study

INTRODUCTION: Connections between environmental factors and mental health issues have been postulated in many different countries around the world. Previously undertaken research has shown many possible connections between these fields, especially in relation to air quality and extreme weather events. However, research on this subject is lacking in New Zealand, which is difficult to analyse as an overall nation due to its many micro-climates and regional differences.OBJECTIVES: The aim of this study and subsequent analysis is to explore the associations between environmental factors and poor mental health outcomes in New Zealand by region and predict the number of people with mental health-related illnesses corresponding to the environmental influence.METHODS: Data are collected from various public-available sources, e.g., Stats NZ and Coronial services of New Zealand, which comprised four environmental factors of our interest and two mental health indicators data ranging from 2016 up until 2020. The four environmental factors are air pollution, earthquakes, rainfall and temperature. Two mental health indicators include the number of people seen by District Health Boards (DHBs) for mental health reasons and the statistics on suicide deaths. The initial analysis is carried out on which regions were most affected by the chosen environmental factors. Further analysis using Auto-Regressive Integrated Moving Average(ARIMA) creates a model based on time series of environmental data to generate estimation for the next two years and mental health projected from the ridge regression.RESULTS: In our initial analysis, the environmental data was graphed along with mental health outcomes in regional charts to identify possible associations. Different regions of New Zealand demonstrate quite different relationships between the environmental data and mental health outcomes. The result of later analysis predicts that the suicide rate and DHB mental health visits may increase in Wellington, drop-in Hawke's Bay and slightly increase in Canterbury for the year 2021 and 2022 with different environmental factors considered.CONCLUSION: It is evident that the relationship between environmental and mental health factors is regional and not national due to the many micro-climates that exist around the nation. However, it was observed that not all factors displayed a good relationship between the regions. We conclude that our hypotheses were partially correct, in that increased air pollution was found to correlate to increased mental health-related DHB visits. Rainfall was also highly correlated to some mental health outcomes. Higher levels of rainfall reduced DHB visits and suicide rates in some areas of the country.

Prediction of Mobility and Burial of Objects on Sandy Seafloor

A numerical model was developed to predict mobility and burial of seafloor cylindrical objects. The model contains four components: 1) object's physical parameters such as diameter, length, mass, and rolling moment; 2) dynamics of rolling cylinder around its major axis; 3) empirical sediment scour model; and 4) seabed environmental characteristics such as currents, waves (peak period, significant wave height), sediment density, and medium sediment grain size. Under the sponsorship of the Department of Defense Strategic Environmental Research and Development Program, a field experiment was conducted from April 21 to May 23, 2013 off the coast of Panama City, FL, USA to measure both objects' mobility using sector scanning and pencil beam sonars and simultaneous environmental time-series data of the boundary layer hydrodynamics and sediment transport conditions for driving mobility. Comparison between modeled and observed data shows the model capability. Future work needs to consider more realistic object shapes and motions such as pitch and yaw, and wavy seabed.

Coupled Delft3D-Object Model to Predict Mobility of Munition on Sandy Seafloor

The coupled Delft3D-object model has been developed to predict the mobility and burial of objects on sandy seafloors. The Delft3D model is used to predict seabed environmental factors such as currents, waves (peak wave period, significant wave height, wave direction), water level, sediment transport, and seabed change, which are taken as the forcing term to the object model consisting of three components: (a) physical parameters such as diameter, length, mass, and rolling moment; (b) dynamics of the rolling cylinder around its major axis; (c) an empirical sediment scour model with re-exposure parameterization. The model is compared with the observational data collected from a field experiment from 21 April to 13 May 2013 off the coast of Panama City, Florida. The experimental data contain both object mobility using sector scanning sonars and maintenance divers as well as simultaneous environmental time series data of the boundary layer hydrodynamics and sediment transport conditions. Comparison between modeled and observed data clearly shows the model’s capabilities and limitations.

Robust Estimation Procedure for Autoregressive Models with Heterogeneity

In environmental studies, regression analysis is frequently performed. The classical approach is the ordinary least squares method which consists in minimizing the sum of the squares of the residuals. However, this method relies on strong assumptions that are not always satisfied. In environmental data, the response variable often contains outliers and errors can be heteroscedastic. This can have significant effects on parameter estimation. To solve this problem, the weighted M-estimation was developed. It assumes a parametric function for the variance, and, estimates alternately and robustly, mean and variance parameters. However, this method is limited to the independent errors case, and is not applicable to time series data. Therefore, we introduce a new estimation procedure which adapts the weighted M-estimation to environmental time series data, while selecting optimal value for the tuning parameter present in the M-estimation. We compare the efficiency of our procedure on simulated data to other usual regression methods. Our estimation procedure outperforms the other methods providing estimates with lower biases and mean squared errors. Finally, we illustrate the proposed method using an air quality dataset from Beijing. This method has been implemented in the R package RlmDataDriven.

Identification of Drivers of Change of the Gulf of Nicoya Ecosystem (Costa Rica)

The Gulf of Nicoya is a large tropical estuary located on the Pacific coast of Costa Rica and accounts for the country’s main fish production. It is increasingly impacted not only by its fisheries, but also by urbanization, tourism developments, the input of pollutants from urban centers and agriculture activities in the catchment areas of large rivers entering the gulf. Similar to other coastal ecosystems, the gulf is particularly sensitive to short- and long-term changes in the climate, such as the precipitation rate, Sea Surface Temperature, wind speed and current regimes. While the gulf has been studied for decades, until now no attempt has been made to combine the analysis of the impacts of fishing and environmental changes on the ecosystem. By following a holistic approach that uses fisheries and environmental time series data from collaborative research and simulation models, this study aims at identifying the main drivers of the observed changes in the Gulf of Nicoya ecosystem. While the model simulations indicate that variations in the catch of some target species (e.g., cephalopods and shrimps) are mainly driven by the fisheries’ exploitation rates, several other species (e.g., corvina, snook, small pelagics, and crabs) are also substantially affected by climate variations, particularly during El Nino periods of high Sea Surface Temperature extremes and increased precipitation. During these periods, phytoplankton productivity and zooplankton biomass deceases with bottom–up effects on the entire food chain. Indicators of the environmental state of the system thus have to be considered along with regulations of the fishing pressure to form the basis for the development of appropriate management strategies.

Surface and sub-surface flow estimation at high temporal resolution using deep neural networks

Recent intensification in climate change have resulted in the rise of hydrological extreme events. This demands modeling of hydrological processes at high temporal resolution to better understand flow patterns in catchments. To model surface and sub-surface flows in a catchment we utilized a physically based model called Hydrological Simulated Program-FORTRAN and two deep learning-based models. One deep learning model consisted of only one long short-term memory (simple LSTM), whereas the other model simulated processes in each hydrological response unit (HRU) by defining one separate LSTM for each HRU (HRU-based LSTM). The models use environmental time-series data and two-dimensional spatial data to predict surface and sub-surface flows at 6-minute time step simultaneously. We tested our models in a tropical humid headwater catchment in northern Lao PDR and compared their performances. Our results showed that the simple LSTM model outperformed the other models on surface runoff prediction with the lowest MSE (7.4e−5 m3 s−1), whereas HRU-based LSTM model better predicted patterns and slopes in sub-surface flow in comparison with the other models by having the smallest MSE value (3.2e−4 m3 s−1). This study demonstrated the performance of a deep learning model when simulating hydrological cycle with high temporal resolution.

Monte Carlo Optimization for Sliding Window Size in Dixon Quality Control of Environmental Monitoring Time Series Data

Outliers are often present in large datasets of water quality monitoring time series data. A method of combining the sliding window technique with Dixon detection criterion for the automatic detection of outliers in time series data is limited by the empirical determination of sliding window sizes. The scientific determination of the optimal sliding window size is very meaningful research work. This paper presents a new Monte Carlo Search Method (MCSM) based on random sampling to optimize the size of the sliding window, which fully takes advantage of computers and statistics. The MCSM was applied in a case study to automatic monitoring data of water quality factors in order to test its validity and usefulness. The results of comparing the accuracy and efficiency of the MCSM show that the new method in this paper is scientific and effective. The experimental results show that, at different sample sizes, the average accuracy is between 58.70% and 75.75%, and the average computation time increase is between 17.09% and 45.53%. In the era of big data in environmental monitoring, the proposed new methods can meet the required accuracy of outlier detection and improve the efficiency of calculation.

Harnessing the power of topological data analysis to detect change points

AbstractWe introduce a novel geometry‐oriented methodology, based on the emerging tools of topological data analysis, into the change‐point detection framework. The key rationale is that change points are likely to be associated with changes in geometry behind the data‐generating process. While the applications of topological data analysis to change‐point detection are potentially very broad, in this paper, we primarily focus on integrating topological concepts with the existing nonparametric methods for change‐point detection. In particular, the proposed new geometry‐oriented approach aims to enhance detection accuracy of distributional regime shift locations. Our simulation studies suggest that integration of topological data analysis with some existing algorithms for change‐point detection leads to consistently more accurate detection results. We illustrate our new methodology in application to the two closely related environmental time series data sets—ice phenology of the Lake Baikal and the North Atlantic Oscillation indices, in a research query for a possible association between their estimated regime shift locations.

Dynamic harmonic regression and irregular sampling; avoiding pre-processing and minimising modelling assumptions

Many environmental time-series measurements are characterised by irregular sampling. A significant improvement of the Dynamic Harmonic Regression (DHR) modelling technique to accommodate irregular sampled time-series, without the need for data pre-processing, has been developed. Taylor's series is used to obtain the time-step state increments, modifying the transition equation matrices. This allows the user to avoid artefacts arising and insertion of assumptions from interpolation and regularisation of the data to a regular time-base and makes DHR more consistent with the Data-Based Mechanistic approach to modelling environmental systems. The new technique implemented as a Matlab package has been tested on demanding simulated data-sets and demonstrated on various environmental time-series data with significantly varying sampling times. The results have been compared with standard DHR, where possible, and the method reduces analysis time and produces unambiguous results (by removing the need for pre-processing – always based on assumptions) based only on the observed environmental data.

Detecting change-point, trend, and seasonality in satellite time series data to track abrupt changes and nonlinear dynamics: A Bayesian ensemble algorithm

Satellite time-series data are bolstering global change research, but their use to elucidate land changes and vegetation dynamics is sensitive to algorithmic choices. Different algorithms often give inconsistent or sometimes conflicting interpretations of the same data. This lack of consensus has adverse implications and can be mitigated via ensemble modeling, an algorithmic paradigm that combines many competing models rather than choosing only a single “best” model. Here we report one such time-series decomposition algorithm for deriving nonlinear ecosystem dynamics across multiple timescales—A Bayesian Estimator of Abrupt change, Seasonal change, and Trend (BEAST). As an ensemble algorithm, BEAST quantifies the relative usefulness of individual decomposition models, leveraging all the models via Bayesian model averaging. We tested it upon simulated, Landsat, and MODIS data. BEAST detected changepoints, seasonality, and trends in the data reliably; it derived realistic nonlinear trends and credible uncertainty measures (e.g., occurrence probability of changepoints over time)—some information difficult to derive by conventional single-best-model algorithms but critical for interpretation of ecosystem dynamics and detection of low-magnitude disturbances. The combination of many models enabled BEAST to alleviate model misspecification, address algorithmic uncertainty, and reduce overfitting. BEAST is generically applicable to time-series data of all kinds. It offers a new analytical option for robust changepoint detection and nonlinear trend analysis and will help exploit environmental time-series data for probing patterns and drivers of ecosystem dynamics.

EcoMem: An R package for quantifying ecological memory

Ecological processes may exhibit memory to past disturbances affecting the resilience of ecosystems to future disturbance. Understanding the role of ecological memory in shaping ecosystem responses to disturbance under global change is a critical step toward developing effective adaptive management strategies to maintain ecosystem function and biodiversity. We developed EcoMem, an R package for quantifying ecological memory functions using common environmental time series data (continuous, count, proportional) applying a Bayesian hierarchical framework. The package estimates memory functions for continuous and binary (e.g., disturbance chronology) variables making no a priori assumption on the form of the functions. EcoMem allows users to quantify ecological memory for a wide range of ecosystem processes and responses. The utility of the package to advance understanding of the memory of ecosystems to environmental drivers is demonstrated using a simulated dataset and a case study assessing the memory of boreal tree growth to insect defoliation.