Indonesia’s urban green spaces dilemma: Balancing law, ecology, and public space, highlighting Jakarta

Mohammad Raditia Pradana^#, Jarot Mulyo Semedi (^# corresponding author)

Human Geography 2026

This article intervenes in debates on how law, ecology, and urban governance produce the idea of “green space.” Using Indonesia's 30% Green Open Space (GOS) mandate as a critical case, it argues that the legal abstraction of ecology into measurable quotas transforms environmental care into bureaucratic representation. In Jakarta, where land scarcity and political competition make the target unattainable, compliance is performed through the counting of roadside strips, cemeteries, and ornamental medians as green space. Drawing on Lefebvre's concept of the production of space, Harvey's spatial justice, and Jacobs's notion of lived urban vitality, the article shows how this abstraction privileges visibility and legitimacy over ecological function. Jakarta exemplifies a global urban condition in which sustainability becomes esthetic, green space becomes arithmetic, and law becomes landscape. The debates call for a redefinition of GOS as spatial care—a relational practice that distinguishes but connects ecological integrity and public accessibility. Moving beyond green quotas toward spatial care, it invites urban geography to reconsider how space is known, governed, and lived in the name of sustainability.

[Paper]

Harmonizing street-view semantics and spatial predictors for dominant urban visual composition modelling

Mohammad Raditia Pradana^#, Muhammad Dimyati, Ahmad Gamal (^# corresponding author)

Computational Urban Science 2025 Spotlight

Street-level visual experiences are underrepresented in top-down spatial datasets such as remote sensing and spatial footprints, which predominantly capture configurations from an overhead perspective. This study develops a framework to model and map urban visual dominance, defined through seven typologies based on Greenness, Openness, and Enclosure. A total of 12,631 Google Street View panoramas were semantically segmented with a pretrained ADE20K deep learning model to extract proportions of trees, buildings, and sky. These proportions were aggregated into 50 m hexagonal grids and classified into visual dominance classes through rule-based logic. To predict these classes beyond street-view coverage, three scenarios of spatial predictors (remote sensing indices, building footprints, and their combination) were evaluated using five machine learning algorithms. Logistic Regression with combined predictors performed best, achieving an accuracy of 0.503 and an AUC-ROC up to 0.85 for the Greenness class. External validation against GHSL settlement data across six urban sites showed soft accuracy scores ranging from 22.33% to 67.23%, with better performance in structured environments than in fragmented residential settings. These findings highlight both the promise and limitations of generalizing street-view visual information from two-dimensional spatial features, offering a scalable approach to bridge the spatial coverage gap and support more human-centered urban landscape analysis.

[Paper]

Tracking Urban Sprawl: A Systematic Review and Bibliometric Analysis of Spatio-Temporal Patterns Using Remote Sensing and GIS

Mohammad Raditia Pradana^#, Muhammad Dimyati (^# corresponding author)

European Journal of Geography 2024

The urban sprawl phenomenon refers to the expansion of urban areas driven by high population growth and migration. A spatio-temporal approach is indispensable in urban sprawl research. Monitoring and evaluating urban sprawl in a region is crucial for controlling drastic environmental changes. Integrated Remote Sensing (RS) and Geographic Information System (GIS) technologies can serve as essential tools for this purpose. The aim of this systematic literature review paper is to gather information on the latest data, methods, and findings to be considered in future urban sprawl research. The PRISMA method was employed, involving filtering from the Scopus database, resulting in 30 papers selected for an in-depth review to address the objectives of this paper. Landsat data remains the preferred choice for monitoring changes due to its extensive historical archive compared to other data sources. Landscape metrics represent a more advanced method com-pared to conventional change detection in quantifying urban sprawl. Other indices and quantifiers are also used to support the quantification of urban sprawl. Two perspectives exist in selecting the study's temporal intervals: consistent and inconsistent, which are adjusted based on the natural characteristics of "change," namely "abrupt" and "gradual." Suggestions for future research include using data with detailed spatial resolution and narrow study intervals while considering the patterns of urban sprawl formation.

[Paper]

Cooling Cities, Warming Communities: Quantifying Climate Resilience in Urban Parks Through Anthropomorphic Mapping and Place Attachment

Investigates climate resilience in urban green spaces by integrating anthropomorphic mapping, place attachment analysis, and street-view imagery to understand the relationship between human perception and adaptive urban landscape design.

Prompting Sustainability: A Comparative Analysis of How Generative AI Interprets and Visualizes Urban 'Sustainable' Streetscapes

Examines how generative AI models interpret and visualize sustainable urban streetscapes through prompt-based analysis, evaluating how AI-generated imagery reflects principles of sustainable urban design and planning.