Modeling Land Use Change in Sana’a City of Yemen with MOLUSCE

Journal of Sensors, Год журнала: 2022, Номер 2022, С. 1 - 15

Опубликована: Окт. 20, 2022

This study provided insight into the size of difference between actual and predicted changes in Landsat 8 satellite imagery for case Sana’a Yemen. The LULC classification was created using data available 2005, 2010, 2015, 2020. It used MOLUSCE tool predicting land 2020, 2025, 2030. objectives this are 1) To compare 2010,2015 2) analyze verify tool’s performance (MOLUSCE). 3) identify effect which evented 2015 on 2020,2025 results were: 1/the effects 2010 showed accuracy reliability due to low before conflict region. 2/the were negative did not support logical trend toward progress where it is natural that human element progresses increasing construction. 3/identify prediction (2020,2025,2030) affected by events conflict, images.

Язык: Английский

---

Patterns of green space change and fragmentation in a rapidly expanding city of northern Ghana, West Africa

City and Environment Interactions, Год журнала: 2023, Номер 21, С. 100136 - 100136

Опубликована: Дек. 19, 2023

Green spaces such as forests, grasslands, and croplands (including gardens) can be found in urban environments. Although they benefit human animal well-being, have become threatened due to rapid growth unplanned development. Yet, little attention has been given studying the dynamics of green sub-Saharan Africa. In this study, we examined land use cover (LULC) change fragmentation (especially, spaces) within second fastest urbanising city Ghana, Tamale. particular, focused our analyses on its core (∼5 km radius around centre) relevance economy society. Landsat data was used estimate metrics past future LULC changes study area from 1990 2052. We clear patterns space decline core: i.e., became patchy over time pattern expected continue future. Additionally, built-up class benefited with latter being significantly negatively correlated population size. Our investigation reveals that protected forests tree plantations contributed a significant proportion available core. However, these areas were becoming increasingly by forest reserve downsizing, indiscriminate activities (e.g., logging encroachment), sale public lands private developers, practices commonly associated growth. Hence, enforcement relevant local legislations 2016 Land Use Spatial Planning Act [Act 925]) coupled integration initiatives policies encourage are needed ensure sustainability ecosystems for well-being humans environment.

Язык: Английский

---

Multilayer perceptron and Markov Chain analysis based hybrid-approach for predicting land use land cover change dynamics with Sentinel-2 imagery

Geocarto International, Год журнала: 2023, Номер 38(1)

Опубликована: Сен. 11, 2023

As urbanization accelerates, the degree of human impact on land use is increasing. Changes in cover (LULC) are widely acknowledged as crucial factors environmental change. The most precise approach to comprehending historical patterns use, types changes that have occurred, driving forces behind them, and overall developments through a rigorous assessment LULC changes. By considering causes dynamics this study, we aim identify changing patterns, gains, losses, spatial trends change from 2015 2022, predict for 2030 Islamabad, Pakistan. Multispectral Sentinel-2 satellite images, devoid cloud cover, were employed discern forecast prospective LULC. Random Forest algorithm was used classify various classes with high accuracy reliability. All classified maps exhibit outstanding accuracy, accuracies exceeding 90%. Multilayer Perceptron Markov Chain Analysis (MLP-MCA) based Hybrid-Approach model time series data future Change 2030. validation forecasted map exhibited an over study revealed built-up expanded by area 90.64 km2 8-year interval (2015 - 2022) using substitution natural resources. Based predictions, it anticipated substantial portion entire area, precisely 58.84%, will transform into terrain significant augmentation region corresponding decline crops, forests, other resources poised imperil sustainability Islamabad. This study's findings can give urban planners policymakers valuable insights shifting LULC, enabling them make informed productive decisions about sustainable development.

Язык: Английский

---

Google Earth Engine for improved spatial planning in agricultural and forested lands: A method for projecting future ecological quality

Remote Sensing Applications Society and Environment, Год журнала: 2023, Номер 32, С. 101078 - 101078

Опубликована: Окт. 27, 2023

Язык: Английский

---

The Rohingya refugee crisis in Bangladesh: assessing the impact on land use patterns and land surface temperature using machine learning

Environmental Monitoring and Assessment, Год журнала: 2024, Номер 196(6)

Опубликована: Май 18, 2024

Язык: Английский

---

Exploring the potentialities and challenges of deep learning for simulation and prediction of urban sprawl features

Data & Policy, Год журнала: 2025, Номер 7

Опубликована: Янв. 1, 2025

Abstract Rapid urbanization poses several challenges, especially when faced with an uncontrolled urban development plan. Therefore, it often leads to anarchic occupation and expansion of cities, resulting in the phenomenon sprawl (US). To support sustainable decision–making planning policy development, a more effective approach addressing this issue through US simulation prediction is essential. Despite work published literature on use deep learning (DL) methods simulate indicators, almost no has been assess what already done, potential, issues, challenges ahead. By synthesising existing research, we aim current landscape DL modelling US. This article elucidates complexities US, focusing its multifaceted implications. Through examination methodologies, highlight their effectiveness capturing complex spatial patterns relationships associated begins by demystifying highlighting challenges. In addition, examines synergy between conventional methods, advantages disadvantages. It emerges that forecasting indicators increasing, potential very promising for guiding strategic decisions control mitigate phenomenon. Of course, not without major both terms data models city policies.

Язык: Английский

---

Energy Demand Forecasting for Hybrid Microgrid Systems Using Machine Learning Models

Proceedings of Engineering and Technology Innovation, Год журнала: 2025, Номер 29, С. 68 - 83

Опубликована: Фев. 10, 2025

This study aims to design energy demand forecasting models for management in hybrid microgrid systems using optimized machine learning techniques. By incorporating temperature, humidity, season, hour of the day, and irradiance, complex relationship between these input parameters yield photovoltaics, generator, grid sources is examined. Five different including linear regression, random forest (RF), support vector artificial neural network, extreme gradient boosting are adopted this study. Evaluation model performance shows that RF best candidate dataset, with a mean-squared error 0.2023, mean absolute 0.0831, root-mean-squared 0.4498, R² score 0.9992. Shapley additive explanations analysis identified key predictors such as hour, irradiation, season while highlighting negative impact humidity day week on demand.

Язык: Английский

---

A mixed training sample-based spectral unmixing analysis for improving fractional abundance estimation of Detroit landscape endmembers using Landsat images

Urban forestry & urban greening, Год журнала: 2025, Номер unknown, С. 128786 - 128786

Опубликована: Март 1, 2025

Язык: Английский

---

Leveraging CA-ANN Modelling for SDGs Alignment: Previse Future Land Use Patterns and their Influence on Mirik Lake of sub-Himalayan region

World Development Sustainability, Год журнала: 2025, Номер unknown, С. 100218 - 100218

Опубликована: Апрель 1, 2025

Язык: Английский

---

Evaluating machine learning algorithms for classifying urban heterogeneous landscapes using GEE

Elsevier eBooks, Год журнала: 2025, Номер unknown, С. 379 - 397

Опубликована: Янв. 1, 2025

Язык: Английский

---