Claim Missing Document
Check
Articles

Found 12 Documents
Search

Evaluation of Google Earth Engine Embedding Dataset for Remote Sensing Image Classification Wijaya, Calvin; Harintaka
Geoid Vol. 21 No. 1 (2026)
Publisher : Departemen Teknik Geomatika ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/geoid.v21i1.8151

Abstract

Google Earth Engine (GEE) has emerged as one of the most powerful cloud-based platforms for processing and analyzing remote sensing imagery. By integrating vast Earth observation archives with scalable computational resources, it provides an accessible environment for researchers, practitioners, and decision-makers. In 2025, Google’s AlphaEarth Foundation introduced a novel embedding model trained on diverse Earth observation datasets available on the GEE server. This model, generated from annual time-series imagery and offered in an analysis-ready format, enables general-purpose applications such as classification, clustering, regression and change detection. Despite its potential, the performance and capabilities of this embedding model remain largely underexplored. This study evaluates the effectiveness of the embedding datasets in GEE for supervised classification method. Comparative experiments were conducted against widely used remote sensing imagery, including Sentinel-2 and Landsat 9 imagery, using multiple algorithms such as K-Neural Network (KNN), Support Vector Machine (SVM), Random Forest (RF), Classification and Regression Trees (CART), and Object-Based Image Analysis (OBIA). In addition, a case study was carried out to examine the use of embedding datasets for mangrove classification. Validation using overall accuracy demonstrates that embedding datasets achieve superior results compared to conventional imagery. Classification using the embedding dataset achieved an average overall accuracy of 94%, outperforming Landsat 9 (83.1%) and Sentinel-2 (82.5%). Moreover, the embedding dataset produced a classification pattern similar to OBIA, even without the need for image segmentation. The findings highlight the potential of embedding datasets to enhance classification accuracy and broaden the scope of remote sensing applications, suggesting new opportunities for leveraging advanced machine learning representations in geospatial analysis.
STUDI EFEKTIVITAS MODUL KIOS MELALUI METODE REGENERATIF DI PASAR GANG CIKINI AMPIUN Wijaya, Calvin; Komala, Olga Nauli
Jurnal Sains, Teknologi, Urban, Perancangan, Arsitektur (Stupa) Vol. 8 No. 1 (2026): APRIL
Publisher : Jurusan Arsitektur dan Perencanaan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24912/stupa.v8i1.37067

Abstract

The Cikini Ampiun Market is one of the traditional markets that has grown in the urban village area of Jakarta with a strong social character but faces various physical problems. The narrow, damp space, lack of natural lighting, and poor air circulation have reduced user comfort and the quality of the market environment. In addition, the dense and disorderly arrangement of stalls also reduces space efficiency and disrupts the social activities that are characteristic of the Cikini community. This study aims to determine the effectiveness of applying kiosk modules as a regenerative architectural approach in improving the quality of Cikini Market, which is defined as the level of achievement in improving natural lighting, air circulation, spatial comfort, and the quality of social interaction. The qualitative research methods used include spatial typology studies, observation of user activities, and analysis of lighting, ventilation, and social interaction aspects. The results of the study show that the application of a 3x3x3 meter kiosk module with an open and flexible system can improve air circulation and natural lighting, as well as create a more adaptive interaction space. Thus, the kiosk module has the potential to be an adaptive regenerative solution to changes in activity needs, environmental conditions, and the social dynamics of market users, while also improving physical conditions and strengthening the social and ecological life of the urban village community. Keywords:  Adaptive; Effectiveness Studies; Kiosk Module; Regenerative Architecture; Urban Village Abstrak Pasar Gang Cikini Ampiun merupakan salah satu pasar rakyat yang tumbuh di kawasan kampung kota Jakarta dengan karakter sosial yang kuat, namun menghadapi berbagai permasalahan fisik. Kondisi ruang yang sempit, lembap, minim pencahayaan alami, serta kurangnya sirkulasi udara menyebabkan turunnya kenyamanan pengguna dan kualitas lingkungan pasar. Selain itu, penataan kios yang padat dan tidak teratur juga menurunkan efisiensi ruang serta mengganggu aktivitas sosial yang menjadi ciri khas masyarakat Cikini. Penelitian ini bertujuan untuk mengetahui efektivitas penerapan modul kios sebagai pendekatan arsitektur regeneratif dalam memperbaiki kualitas ruang Pasar Cikini, yang dimaknai sebagai tingkat ketercapaian peningkatan pencahayaan alami, sirkulasi udara, kenyamanan ruang, serta kualitas interaksi sosial. Metode penelitian kualitatif yang digunakan meliputi studi tipologi ruang, observasi aktivitas pengguna, serta analisis terhadap aspek pencahayaan, ventilasi, dan interaksi sosial. Hasil penelitian menunjukkan bahwa penerapan modul kios berukuran 3x3x3 meter dengan sistem terbuka dan fleksibel mampu meningkatkan sirkulasi udara, pencahayaan alami, serta menciptakan ruang interaksi yang lebih adaptif. Dengan demikian, modul kios berpotensi menjadi solusi regeneratif yang adaptif terhadap perubahan kebutuhan aktivitas, kondisi lingkungan, dinamika sosial pengguna pasar, memperbaiki kondisi fisik, dan memperkuat kehidupan sosial dan ekologis masyarakat kampung kota.