Lam Kuok Choy

Rapid urbanization globally has intensified the need for sustainable administrative partitioning, yet spatial methodologies are rarely integrated into governance feasibility frameworks. While regional proliferation in Indonesia is traditionally dictated by administrative, demographic, and financial thresholds, it heavily lacks spatial-functional evaluation regarding land suitability and growth capacity. A critical gap remains in combining quantitative spatial modeling with policy-driven institutional assessments to determine the true spatial readiness of emerging autonomous regions. This study aims to evaluate the feasibility of the Jatinangor Urban Area as a candidate for a New Autonomous Region (DOB) through spatial modeling that combines urban growth data, spatial structure, development suitability, and institutional readiness. Urban change are derived from land cover data from 2017 to 2025 analyzed using Sentinel-2 imagery and the Random Forest algorithm, while projections for 2035 are analyzed using Cellular Automata–Markov. Moran’s I and LISA analyses are used to identify spatial clustering patterns and core–periphery city structures. The Analytical Hierarchy Process (AHP) and Geographic Information Systems (GIS) are used to model development suitability, synthesized through Spatially-Informed SWOT. The results show rapid and uneven urban transformation spatially, with built-up areas increasing from 57.30 km² (2017) to 76.68 km² (2025), and projected to reach 83.53 km² (2035), accompanied by a decrease in agricultural land. A total of 6,104.46 hectares are highly suitable for growth center development, mainly concentrated along the Jatinangor–Cimanggung corridor and part of Pamulihan. Sukasari and similar peripheral zones still struggle with natural constraints. From an administrative view, Jatinangor actually clears the requirements for DOB establishment, but the spatial data shows a different situation. The functional readiness is highly uneven. We found a clear core-periphery gap where public facilities and economic power are centered in one place, leaving the outer areas behind in terms of access. This study recommends that the feasibility of a DOB is not only about meeting administrative requirements but must also be understood spatially to ensure functional integration, equitable service distribution, economic resilience, and environmental sustainability.

Conventional evaluations of rainfall prediction models rely on average accuracy, often masking the conditions, locations and causes of model failure and reduced reliability. This study proposes a paradigm shift from conventional average-accuracy benchmarking toward failure-aware forecast-error diagnosis in the Bengawan Solo River Basin, a tropical monsoon river basin in Indonesia with moderate topographic gradients (grid elevations span ≈ 300–650 m). Methodologically, forecasts from previously published models are treated as fixed inputs and their errors are modelled as the response variable, so the analysis diagnoses when and where models fail rather than retraining them. By treating forecast errors as response variables, rather than as random residuals, this study analyses 345,180 model–grid records–month records from ten individual models (RF, XGB, LGBM, SVR, MLP, LSTM, GRU, TCN, CNN, Transformer) and one best ensemble model (Ensemble_Q, a stacking of RF, XGB, SVR, MLP, LGBM, LSTM, GRU, TCN, CNN, Transformer) against observed CHIRPS (Climate Hazards Group InfraRed Precipitation with Station data) precipitation, seasonal phase, ENSO and IOD regimes (El Niño–Southern Oscillation and Indian Ocean Dipole, respectively), the MJO index (Madden–Julian Oscillation) as an additional analysis, and elevation as a topographic control, using log-error models, high-error logistic regression, interaction tests, and block bootstrap validation (N = 1000), false discovery rate, and spatial statistics. Results indicate that prediction errors are not random but are systematically controlled: the Transition II phase increases log-error by 245% (pooled log-error model) and raises the odds of a high-error event roughly 40-fold relative to the dry season; La Niña conditions amplify errors by 41% and the odds of a high-error event by 3.3 times (though this ENSO signal is largely entangled with co-occurring Negative-IOD months), and every 100 m increase in elevation increases errors by 26%, with errors forming distinct spatial clusters (Moran’s I = 0.78; p = 0.001). Ensemble_Q outperforms the baseline on an aggregate basis (mean absolute error, MAE = 54.10 mm) but still experiences error amplification under these conditions, while spatial deep-learning architectures (TCN, CNN, Transformer) prove most vulnerable to elevation gradients. All major patterns persisted across variations in thresholds, model subsets, ENSO definitions, multiplicity corrections, and bootstrapping. These findings confirm that superior mean accuracy does not guarantee operational reliability, and that conditional failure diagnosis is an essential complement to benchmarking rainfall predictions in tropical monsoon regions.

Local climate zones (LCZs) were originally proposed to redefine the rural–urban dichotomy, while providing a standardised framework for urban heat island (UHI) studies worldwide. The UHI phenomenon, characterised by rising land surface temperature (LST), particularly in urban areas, has become a global urban environmental issue. At the same time, experts project that cities in tropical macroclimate regions will experience UHI effects more rapidly. Therefore, this literature review examines the development of the LCZ framework and identifies future research directions to address global climate change, particularly within tropical urban environments. The study employs the PRISMA framework within the Scopus database, identifying 51 documents suitable for further analysis. Descriptive analysis indicates that LCZ studies are distributed across 60 cities, with Nagpur (India) being the most prominent. Meanwhile, the publication frequency fluctuates, with 2024 recording the highest number. A bibliometric analysis of authors revealed that at least 10 of the most productive researchers originated from different countries, institutions and disciplines. In addition, a bibliometric analysis of keywords identified 18 terms with the highest co‑occurrence rates, which constitute the themes of current LCZ research. Remote sensing (RS)-based methods, employing supervised pixel-based analysis with a random forest classifier developed within the WUDAPT project, dominate LCZ mapping approaches, alongside expert-based and geographic information system (GIS)-based methods. Based on a thematic analysis, the applications of LCZ across various fields include the UHI effect and its mitigation, surface temperature monitoring, heat risk, heat stress and heat hazards, thermal comfort, energy consumption and balance, urban climate modelling, urban planning, and other applications such as urban health and air quality. In the future, LCZ in tropical macroclimate regions is likely to become a highly complex field of study, requiring the involvement of multidisciplinary approaches.

Remote sensing object detection faces persistent challenges from scale diversity, cluttered scenes, and resolution constraints, often leading to suboptimal performance on small or overlapping targets. To mitigate these limitations, we introduce MSAF-Net, a novel architecture designed to improve multi-resolution feature learning through refined attention mechanisms. The model incorporates coordinated spatial and channel-wise attention across network stages to adaptively highlight informative regions and suppress background interference. Furthermore, we develop a scale-aware feature fusion approach that aligns representations from different layers, enabling more accurate detection of objects across a wide range of scales. Experimental evaluations on standard benchmarks, including DOTA and NWPU VHR-10, confirm that MSAF-Net achieves notable gains over state-of-the-art methods in both precision and recall. These findings demonstrate the potential of attention-guided strategies in enhancing object detection for high-resolution remote sensing imagery.

Reliable spatio-temporal rainfall prediction is a key element in disaster mitigation and water resource management in dynamic tropical regions such as the Bengawan Solo River Watershed. However, high climate variability and data limitations often pose significant challenges to the accuracy of conventional prediction models. This study introduces an innovative approach by applying ensemble stacking, which combines machine learning models such as Random Forest (RF), Extreme Gradient Boosting (XGB), Support Vector Regression (SVR), Multi-Layer Perceptron (MLP), Light Gradient-Boosting Machine (LGBM) and deep learning models like Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Temporal Convolutional Networks (TCN), Convolutional Neural Network (CNN), and Transformer architecture based on monthly Climate Hazards Group InfraRed Precipitation with Stations (CHIRPS) data (1981–2024). The novelty of this research lies in the systematic exploration of various model combination scenarios—both classical and deep learning and the evaluation of their performance in projecting rainfall for 2025–2030. All base models were trained on the 1981–2019 period and validated with data from the 2020–2024 period, while ensemble stacking was developed using a linear regression meta-learner. The results show that the optimal ensemble scenario reduces the MAE to 53.735 mm, the RMSE to 69.242 mm, and increases the R² to 0.795826—better than all individual models. Spatial and temporal analyses also indicate consistent model performance at most locations and times. Annual rainfall projections for 2025–2030 were then interpolated using IDW to generate a spatio-temporal rainfall distribution map. The improved accuracy provides a strong scientific basis for disaster preparedness, flood and drought management, and sustainable water planning in the Bengawan Solo River Watershed. Beyond this case, the approach demonstrates significant transferability to other climate-sensitive and data-scarce regions.

The Pacitan Regency is at risk of megathrust earthquakes and tsunamis due to the seismic gap along the southern region of Java Island, making risk-reduction efforts crucial. This research aims to analyse the tsunami risk associated with a potential megathrust earthquake scenario in Pacitan’s coastal areas and develop sustainable mitigation strategies. The research employs spatial analysis to evaluate the risk and subsequently formulate strategies for long-term mitigation. A weighted overlay method was utilised to integrate hazard (H) and vulnerability (V) datasets to produce a tsunami risk map (R). The hazard component was modelled using a tsunami propagation simulation based on the Shallow Water Equations in the Delft3D-Flow software, incorporating an earthquake scenario of Mw 8.8 and H-loss calculations in ArcGIS Pro 10.3. The vulnerability assessment was conducted by overlaying population density, land use, and building footprint from the Global Human Settlement Layer (GHSL) datasets. Finally, sustainable strategies were proposed to mitigate the tsunami risk effectively. The results show that Pacitan faces significant tsunami disaster risk, with tsunami waves at the coast reaching 16.6 m. Because the coast of Pacitan is densely populated, mitigation strategies are necessary, and in the present contribution, the authors developed holistic spatial planning, which prioritise the preservation and restoration of natural barriers, such as mangroves and coastal forests.

Impacts of urban land use and land cover changes on land surface temperature in Kuala Lumpur, Malaysia

Landscape dynamics reflected in changes in land use have been proven to have changed environmental quality in many countries (Roy et al. 2022). Landscape dynamics occur massively in many countries ...

Fine particulate matter is one of the atmospheric contaminants that exist in the atmosphere. The purpose of this study is to evaluate spatial–temporal changes in PM_2.5 concentrations in the central and south zones of Peninsular Malaysia from 2019 to 2020. The study area involves twenty-one monitoring stations in the central and south zones of Peninsular Malaysia, using monthly and annual means of PM_2.5 concentrations. The spatial autocorrelation of PM_2.5 is calculated using Moran’s I, while three semi-variogram models are used to measure the spatial variability of PM_2.5. Three kriging methods, ordinary kriging (OK), simple kriging (SK), and universal kriging (UK), were used for interpolation and comparison. The results showed that the Gaussian model was more appropriate for the central zone (MSE = 14.76) in 2019, while the stable model was more suitable in 2020 (MSE = 19.83). In addition, the stable model is more appropriate for both 2019 (MSE = 12.68) and 2020 (8.87) for the south zone. Based on the performance indicator, universal kriging was chosen as the best interpolation method in 2019 and 2020 for both the central and south zone. In conclusion, the findings provide a complete map of the variations in PM_2.5 for two different zones, and show that interpolation methods such as universal kriging are beneficial and could be extended to the investigation of air pollution distributions in other areas of Peninsular Malaysia.

A Corpus-Assisted Discourse Analysis Case Study of Public Opinion on Climate Change in Malaysia