A framework for climate change assessment in Mediterranean data-sparse watersheds using remote sensing and ARIMA modeling

Sayah, Mario J. Al; Abdallah, Chadi; Khouri, Michel; Nedjaï, Rachid; Darwich, Talal

doi:10.1007/s00704-020-03442-7

Cited by 19 publications

(5 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In ARIMA, p represents the order of autoregression and q is the representation of the order of moving average [79]. To check the stationarity of the original data, the Dickey-Fuller unit root (ADF) test is a common method; if the test results suggest that the data are nonstationary, then differencing is applied to data to make in stationary [80]. When variance and mean of time series data are time-independent, then a time series is considered as stationary series [81].…”

Section: Arima Modelingmentioning

confidence: 99%

Time Series Analyses and Forecasting of Surface Urban Heat Island Intensity Using ARIMA Model in Punjab, Pakistan

Mehmood

Zafar

Sajjad

et al. 2022

Land

View full text Add to dashboard Cite

In the context of rapid urbanization, Urban Heat Island (UHI) is considered as a major anthropogenic alteration in Earth environments, and its temporal trends and future forecasts for large areas did not receive much attention. Using land surface temperature (LST) data from MODIS (Moderate Resolution Imaging Spectro-radiometer) for years 2006 to 2020, we quantified the temporal trends of daytime and nighttime surface UHI intensity (SUHII, difference of urban temperature to rural temperature) using the Mann-Kendall (MK) trend test in six major cities of the Punjab province of Pakistan and estimated the future SUHII for the year 2030 using the ARIMA model. Results from the study revealed that the average mean SUHII for daytime was noted as 2.221 °C and the average mean nighttime SUHII was noted as 2.82 °C for the years 2006 to 2020. The average mean SUHII for daytime and nighttime exhibited increasing trends for all seasons and annually, and for the daytime spring season it showed a maximum upward trend of 0.486 °C/year (p < 0.05) and for the nighttime annual SUHII with an increasing rate of 0.485 °C/year (p < 0.05) which exhibited a maximum upward trend. The ARIMA model forecast suggested an increase of 0.04 °C in the average daytime SUHII and an increase of 0.1 °C in the average nighttime SUHII until 2030. The results from this study highlight the increasing trends of daytime and nighttime SUHII, ARIMA also forecasted an increase in daytime and nighttime SUHII, suggesting various strategies are needed for an effective mitigation of the UHI effect.

show abstract

Section: Arima Modelingmentioning

confidence: 99%

Time Series Analyses and Forecasting of Surface Urban Heat Island Intensity Using ARIMA Model in Punjab, Pakistan

Mehmood

Zafar

Sajjad

et al. 2022

Land

View full text Add to dashboard Cite

show abstract

“…Earth observation (EO) via remote sensing technologies provides information about our planet's physical, chemical, and biological systems [1]. This type of information is crucial in regions which are exposed in various risks (e.g., climate change, droughts, floods, earthquakes, and landslides) and where ground data are scarce [2][3][4][5], such as the Eastern Mediterranean, Middle East, and North Africa (EMMENA) region [6].…”

Section: Introductionmentioning

confidence: 99%

Earth Observation in the EMMENA Region: Scoping Review of Current Applications and Knowledge Gaps

Eliades,

Michaelides,

Evagorou

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Earth observation (EO) techniques have significantly evolved over time, covering a wide range of applications in different domains. The scope of this study is to review the research conducted on EO in the Eastern Mediterranean, Middle East, and North Africa (EMMENA) region and to identify the main knowledge gaps. We searched through the Web of Science database for papers published between 2018 and 2022 for EO studies in the EMMENA. We categorized the papers in the following thematic areas: atmosphere, water, agriculture, land, disaster risk reduction (DRR), cultural heritage, energy, marine safety and security (MSS), and big Earth data (BED); 6647 papers were found with the highest number of publications in the thematic areas of BED (27%) and land (22%). Most of the EMMENA countries are surrounded by sea, yet there was a very small number of studies on MSS (0.9% of total number of papers). This study detected a gap in fundamental research in the BED thematic area. Other future needs identified by this study are the limited availability of very high-resolution and near-real-time remote sensing data, the lack of harmonized methodologies and the need for further development of models, algorithms, early warning systems, and services.

show abstract

“…Te short-term trafc fow is characterized by time series. Te traditional time series prediction is a linear ftting method represented by autoregressive integrated moving average (ARIMA) [2,3]. Tis method has a problem of poor ability to ft nonlinear data [4].…”

Section: Introductionmentioning

confidence: 99%

“…However, these models still have some drawbacks: (1) gradient explosion and gradient disappearance for long period time series; (2) with the increase of the sequence length, it is easy to lose information due to the weak extraction ability on key information.…”

Section: Introductionmentioning

confidence: 99%

An Effective Self-Attention-Based Hybrid Model for Short-Term Traffic Flow Prediction

Wang

Yang

2023

Advances in Civil Engineering

View full text Add to dashboard Cite

Vehicle exhaust is one of the main sources of carbon emissions. The short-term traffic flow prediction plays an important role in alleviating traffic congestion, optimizing the travel structure, and reducing traffic carbon emissions. The current advanced models of short-term traffic flow prediction are evaluated in this work, especially their inadequacies. To improve the prediction accuracy and ensure fine traffic management, an effective self-attention-based hybrid model is proposed to predict the short-term traffic flow. The proposed model includes an encoder-decoder neural network module and a self-attention mechanism module. The self-attention mechanism module is applied as a feature extraction unit in this hybrid model to enhance the ability of key information capture and to settle the problem on key information disappearing due to the increasing sequence length in traditional models. The dataset of the Guangdong freeway toll station is used for the experimental testing. Compared with several baseline models, the proposed model is more suitable for real-time prediction and can provide highly accurate results. Also, a better interpretability is presented in this proposed model. The experimental results showed that MAE, RMSE, and MAPE of the proposed model are 3.01, 4.38, and 12.99%, respectively. Our new hybrid model gives a higher accuracy than the support vector regression (SVR) model, LSTM neural network-attention (LSTM-attention) model, and temporal convolutional network (TCN) model. It shows that the proposed model in this work is favorable to the short-term traffic flow prediction.

show abstract

A framework for climate change assessment in Mediterranean data-sparse watersheds using remote sensing and ARIMA modeling

Cited by 19 publications

References 55 publications

Time Series Analyses and Forecasting of Surface Urban Heat Island Intensity Using ARIMA Model in Punjab, Pakistan

Time Series Analyses and Forecasting of Surface Urban Heat Island Intensity Using ARIMA Model in Punjab, Pakistan

Earth Observation in the EMMENA Region: Scoping Review of Current Applications and Knowledge Gaps

An Effective Self-Attention-Based Hybrid Model for Short-Term Traffic Flow Prediction

Contact Info

Product

Resources

About