Naheem Adebisi

Bio: Naheem Adebisi is an academic researcher from Universiti Teknologi Petronas. The author has contributed to research in topics: Air quality index & Tide gauge. The author has an hindex of 2, co-authored 6 publications receiving 15 citations.

Sea level prediction using ARIMA, SVR and LSTM neural network: assessing the impact of ensemble Ocean-Atmospheric processes on models’ accuracy

Abstract: This study aims to integrate a broad spectrum of ocean-atmospheric variables to predict sea level variation along West Peninsular Malaysia coastline using machine learning and deep learning techniq...

A review of the inter-correlation of climate change, air pollution and urban sustainability using novel machine learning algorithms and spatial information science

Abstract: Air pollution is a global geo-hazard with significant implications, including deterioration of health and premature death. Climatic variables such as temperature, rainfall, wind, and humidity impact air pollution by affecting the strength, transportation, and dispersion of pollutants in the atmosphere. Emerging data science tools, particularly Machine Learning (ML) big data analytics, are being utilized to predict air pollution intensity and frequency under varying climatic conditions for effective mitigation plans. However, comprehensive documentation of these digitalization approaches and outcomes in terms of correlating future air pollution with climate change remains scant. This study addresses this gap by systematically reviewing pertinent literature on climate change and air pollution studies. We also investigated the potentials of integrated spatial data science for spatial modelling and identifying cities vulnerable to air pollution hazards. Our findings show that climatic factors and seasonal variations are critical predictors of air quality in urban areas. A strong correlation exists between climate change and air quality, and air quality in urbanized regions is projected to deteriorate with climate change in the future. Therefore, climatic variables remain essential factors for the prediction of air quality. Also, air pollutants tend to have higher concentration in the warm season, making the consideration of seasonal changes crucial in air quality management. The study also revealed that machine learning algorithms such as random forest, gradient boosting machine, and classification and regression trees (CART) accurately predict air pollution hazard when integrated with spatial models. The detailed review of literature undertaken in this study provides a strong basis for the conclusion that the integration of spatial techniques and machine learning has the potential to improve air pollution prediction outcome and aid appropriate intervention initiatives by the stakeholders. Thus, emerging geospatial intelligence technologies and digital innovations particularly Artificial intelligence, machine learning and big data analytics that underpin the fourth industrial revolution (IR 4.0) can enhance existing early warning mechanisms and support a prompt and effective response to climate-change-induced air pollution, thereby fostering sustainable cities and societies.

Digitalization for transformative urbanization, climate change adaptation, and sustainable farming in Africa: trend, opportunities, and challenges

Abstract: ABSTRACT In sub-Saharan Africa, mass rural-urban migration negatively affectthe agriculture sector that accounts for about 23% of the GDP and employs over 60% of the population. Together with a rapidly changing climate, unplanned urbanization poses serious threats to Africa’s agriculture sector with the risk of chronic food shortages in the future. To stem this tide, it is imperative to systematically assess the unplanned urbanization trend from a socio-economic perspective and distill the broader implication for sustainable urban farming within the context of climate change in the region. The potentials of digitalization as a tool for transformative adaptation to climate change and enabler of sustainable development in different domains, including agriculture, are beginning to emerge. However, most studies are based on data from Asia, Europe, North America, and Oceania. There is minimal documentation of current applications and prospects of digitalization for sustainable agricultural practices in Africa, particularly in an increasingly urbanized era. Thus, this study addresses this need by evaluating the potentials of digitalization to enable sustainable farming in the face of unprecedented climate change constraints in Africa and minimize the negative impacts of urbanization on agriculture. Through a desk research approach, the present study explores the challenges to digital farming in Africa despite its successful implementation in the global North. Drawing lessons from successful case-studies worldwide, we suggest possible pathways to overcome the challenges and implement localized digitalization approaches to strengthen preventive action against climate risks, enhance disaster preparedness, and aid effective planning and management of agriculture practices. Integrating agriculture into the city via digital urban farming is crucial for long-term food security and creating appealing clean-tech jobs for a large number of new immigrants, thereby supporting African cities’ resilience and sustainable development.

Big Data for Healthcare Industry 4.0: Applications, challenges and future perspectives

Abstract: The innovative technologies emerged with the industrial revolution “Industry 4.0” as well as the new ones on the way of advanced digitalization enable delivering enhanced, value-added and cost-effective manufacturing and service operations. One of the first areas of focus for Industry 4.0 applications is operations related to healthcare services. Effective management of healthcare resources, clinical care processes, service planning, delivery and evaluation of healthcare operations are essential for a well-functioning healthcare system. Yet, with the adoption of technologies such as Internet of Health Things, Medical Cyber–Physical Systems, Machine Learning, and Big Data (BD), the healthcare sector has recognized the relevance of Industry 4.0. The concept of BD offered numerous advantages and opportunities in this field. It changed the way information is gathered, shared and utilized. Hence, in this study our main ambition is to provide readers with a review of publications which lie within the intersection of Industry 4.0, BD, and healthcare operations and give future perspectives. Our review shows that BD constitutes an important place on the technologies Industry 4.0 provides in the healthcare domain. It helps design, improve, analyze, assess and optimize operations in the domain.

Performance Comparison of an LSTM-based Deep Learning Model versus Conventional Machine Learning Algorithms for Streamflow Forecasting

Abstract: Streamflow forecasting plays a key role in improvement of water resource allocation, management and planning, flood warning and forecasting, and mitigation of flood damages. There are a considerable number of forecasting models and techniques that have been employed in streamflow forecasting and gained importance in hydrological studies in recent decades. In this study, the main objective was to compare the accuracy of four data-driven techniques of Linear Regression (LR), Multilayer Perceptron (MLP), Support Vector Machine (SVM), and Long Short-Term Memory (LSTM) network in daily streamflow forecasting. For this purpose, three scenarios were defined based on historical precipitation and streamflow series for 26 years of the Kentucky River basin located in eastern Kentucky, US. Statistical criteria including the coefficient of correlation ( $$R$$ ), Nash-Sutcliff coefficient of efficiency ( $$E$$ ), Nash-Sutcliff for High flow ( $${E}_{H}$$ ), Nash-Sutcliff for Low flow ( $${E}_{L}$$ ), normalized root mean square error ( $$NRMSE$$ ), relative error in estimating maximum flow ( $$REmax$$ ), threshold statistics ( $$TS$$ ), and average absolute relative error ( $$AARE$$ ) were employed to compare the performances of these methods. The results show that the LSTM network outperforms the other models in forecasting daily streamflow with the lowest values of $$NRMSE$$ and the highest values of $${E}_{H}$$ , $${E}_{L}$$ , and $$R$$ under all scenarios. These findings indicated that the LSTM is a robust data-driven technique to characterize the time series behaviors in hydrological modeling applications.

Long Term and Recent Changes in Sea Level in the Falkland Islands

Abstract: [1] Mean sea level measurements made at Port Louis in the Falkland Islands in 1981–1982, 1984, and 2009, together with values from the nearby permanent tide gauge at Port Stanley, have been compared to measurements made at Port Louis in 1842 by James Clark Ross. The long-term rate of change of sea level is estimated to have been +0.75 ± 0.35 mm/yr between 1842 and the early 1980s, after correction for air pressure effects and for vertical land movement due to glacial isostatic adjustment (GIA). The 2009 Port Louis data set is of particular importance due to the availability of simultaneous information from Port Stanley. The data set has been employed in two ways, by providing a short recent estimate of mean sea level itself, and by enabling the effective combination of measurements at the two sites. The rate of sea level rise observed since 1992, when the modern Stanley gauge was installed, has been larger at 2.51 ± 0.58 mm/yr, after correction for air pressure and GIA. This rate compares to a value of 2.79 ± 0.42 mm/yr obtained from satellite altimetry in the region over the same period. Such a relatively recent acceleration in the rate of sea level rise is consistent with findings from other locations in the Southern Hemisphere and globally.

A new atmospheric proxy for sea level variability in the southeastern North Sea: observations and future ensemble projections

Abstract: Atmosphere–ocean interactions are known to dominate seasonal to decadal sea level variability in the southeastern North Sea. In this study an atmospheric proxy for the observed sea level variability in the German Bight is introduced. Monthly mean sea level (MSL) time series from 13 tide gauges located in the German Bight and one virtual station record are evaluated in comparison to sea level pressure fields over the North Atlantic and Europe. A quasi-linear relationship between MSL in the German Bight and sea level pressure over Scandinavia and the Iberian Peninsula is found. This relationship is used (1) to evaluate the atmospheric contribution to MSL variability in hindcast experiments over the period from 1871–2008 with data from the twentieth century reanalysis v2 (20CRv2), (2) to isolate the high frequency meteorological variability of MSL from longer-term changes, (3) to derive ensemble projections of the atmospheric contribution to MSL until 2100 with eight different coupled global atmosphere–ocean models (AOGCM’s) under the A1B emission scenario and (4) two additional projections for one AOGCM (ECHAM5/MPI-OM) under the B1 and A2 emission scenarios. The hindcast produces a reasonable good reconstruction explaining approximately 80 % of the observed MSL variability over the period from 1871 to 2008. Observational features such as the divergent seasonal trend development in the second half of the twentieth century, i.e. larger trends from January to March compared to the rest of the year, and regional variations along the German North Sea coastline in trends and variability are well described. For the period from 1961 to 1990 the Kolmogorov-Smirnow test is used to evaluate the ability of the eight AOGCMs to reproduce the observed statistical properties of MSL variations. All models are able to reproduce the statistical distribution of atmospheric MSL. For the target year 2100 the models point to a slight increase in the atmospheric component of MSL with generally larger changes during winter months (October–March). Largest MSL changes in the order of ~5–6 cm are found for the high emission scenario A2, whereas the moderate B1 and intermediate A1B scenarios lead to moderate changes in the order of ~3 cm. All models point to an increasing atmospheric contribution to MSL in the German Bight, but the uncertainties are considerable, i.e. model and scenario uncertainties are in the same order of magnitude.

A review of the inter-correlation of climate change, air pollution and urban sustainability using novel machine learning algorithms and spatial information science

Abstract: Air pollution is a global geo-hazard with significant implications, including deterioration of health and premature death. Climatic variables such as temperature, rainfall, wind, and humidity impact air pollution by affecting the strength, transportation, and dispersion of pollutants in the atmosphere. Emerging data science tools, particularly Machine Learning (ML) big data analytics, are being utilized to predict air pollution intensity and frequency under varying climatic conditions for effective mitigation plans. However, comprehensive documentation of these digitalization approaches and outcomes in terms of correlating future air pollution with climate change remains scant. This study addresses this gap by systematically reviewing pertinent literature on climate change and air pollution studies. We also investigated the potentials of integrated spatial data science for spatial modelling and identifying cities vulnerable to air pollution hazards. Our findings show that climatic factors and seasonal variations are critical predictors of air quality in urban areas. A strong correlation exists between climate change and air quality, and air quality in urbanized regions is projected to deteriorate with climate change in the future. Therefore, climatic variables remain essential factors for the prediction of air quality. Also, air pollutants tend to have higher concentration in the warm season, making the consideration of seasonal changes crucial in air quality management. The study also revealed that machine learning algorithms such as random forest, gradient boosting machine, and classification and regression trees (CART) accurately predict air pollution hazard when integrated with spatial models. The detailed review of literature undertaken in this study provides a strong basis for the conclusion that the integration of spatial techniques and machine learning has the potential to improve air pollution prediction outcome and aid appropriate intervention initiatives by the stakeholders. Thus, emerging geospatial intelligence technologies and digital innovations particularly Artificial intelligence, machine learning and big data analytics that underpin the fourth industrial revolution (IR 4.0) can enhance existing early warning mechanisms and support a prompt and effective response to climate-change-induced air pollution, thereby fostering sustainable cities and societies.