Skip to content

Kevin Muiruri

Research interests: project delivery methods and impact to project success; project control and construction contracts; privatization in construction and private-public partnerships; project cost management; sustainability.

M.S. Construction Management, University of Washington (2022)
B.S. Civil Engineering, Dedan Kimathi University of Technology, Kenya (2017)

Associate Professor Manish Chalana Embarking on Fulbright-Nehru Fellowship March 2024

Historic preservation (or “heritage conservation” in India) is the practice of identifying, managing, and interpreting the historical record in the built environment. For many people, the resulting presence of these tangible reminders in their day-to-day world plays a major role in shaping their perceptions of who has contributed what to their nation’s development. The magnitude and challenges of these tasks have increased dramatically in contemporary times, as the field has begun to grapple with the complexity of history. This is…

Zeyu Wang

Research Interests: Geospatial big data, travel behavior, human mobility, built environment assessment

Detecting Subpixel Human Settlements in Mountains Using Deep Learning: A Case of the Hindu Kush Himalaya 1990–2020

Chen, T.-H. K., Pandey, B., & Seto, K. C. (2023). Detecting subpixel human settlements in mountains using deep learning: A case of the Hindu Kush Himalaya 1990–2020. Remote Sensing of Environment, 294, 113625–. https://doi.org/10.1016/j.rse.2023.113625

View Publication

Abstract

The majority of future population growth in mountains will occur in small- and medium-sized cities and towns and affect vulnerable ecosystems. However, mountain settlements are often omitted from global land cover analyses due to the low spatial resolution of satellite images, which cannot resolve the small scale of mountains settlements. This study demonstrates, for the first time, the potential of deep learning to detect human settlements in mountains at the sub-pixel level, based on Landsat satellite imagery. We hypothesized that adding spatial and temporal features could improve the detection of mountain settlements since spectral information alone led to inaccurate results. For spatial features, we compared a U-shaped neural network (U-Net), a deep learning algorithm that automatically learns spatial features, with a simple random forest (RF) algorithm. Then, we assessed whether temporal features would increase accuracy by comparing two input datasets, multispectral imagery and temporal features from the Continuous Change Detection and Classification (CCDC) algorithm. We evaluated each method by calculating the accuracies of (1) the binary settlement footprint, (2) the subpixel estimates of impervious surfaces, and (3) urban growth. We tested the accuracies using visually interpreted datasets from time-series Google Earth images across the Hindu Kush Himalaya that were not used for training to evaluate model transferability. The U-Net successfully improved mountain settlement mapping compared to the random forest, with a substantial discrepancy in small settlements. The time-series results from the U-Net successfully captured long-term urban growth but fewer short-term changes. Contrary to expectations, the CCDC temporal features reduced the accuracy of mountain settlement mapping due to frequent cloud cover in hilly areas. Our subpixel analysis reveals that the built-up area of the Hindu Kush Himalaya has expanded at a rate of 61 km2 per year from 1990 to 2020, which is about twice the estimate of the Global Human Settlement Layer using binary urban/non-urban classifications.

Keywords

Urban land cover; Land cover fraction; Peri-urban; Built-up area; Subpixel mapping; Machine learning; Time-series; Himalaya; CCDC

College of Built Environments Announces 2023 Inspire Fund Awards

In 2021, the College of Built Environments launched the CBE Inspire Fund to “inspire” CBE research activities that are often underfunded, but for which a relatively small amount of support can be transformative. The Inspire Fund aims to support research where arts and humanities disciplines are centered, and community partners are engaged in substantive ways. Inspire Fund is also meant to support ‘seed’ projects, where a small investment in early research efforts may serve as a powerful lever for future…

Digital Governance in Rural Chengdu, China: Its Potential for Social-ecological Resilience

Wu, Shuang, Abramson, Daniel B., & Zhong, Bo. (2022). Digital Governance in Rural Chengdu, China: Its Potential for Social-ecological Resilience. Frontiers in Sustainable Cities, 4.

View Publication

Abstract

In this study, we echo the call from the UN to interpret Sustainable Development Goals (SDGs) in their regional context—in this case, the linpan (wooded lot) landscape of the Chengdu Plain, in Sichuan, China, where the shocks and stresses of recent, rapid administrative-economic urbanization are testing the resilience of some of the world's most sustainably productive and long- and densely-settled agrarian environments. In recent years, fine-grained information and communications technology (ICT) governance tools in Chengdu, such as “grid management”, present opportunities to sustain and scale up the collection of data necessary to validate and refine indicators of landscape resilience, and use them to regulate development, in accordance with SDG goal 11 to enhance legislation, governance, and capacity via information gathering and sharing. ICT-based governance in combination with traditional place-based knowledge can play a critical role in ensuring the resilience of urban-rural co-development. To realize this potential, however, ICT-enabled governance needs to incorporate greater transparency and more local feedback loops and enable greater participation from older farmers and women, to inform household and community-level land-use choices and initiatives. It also needs to link regulatory functions with marketing and pricing functions so that farmers may benefit from the sustainable practices they are encouraged to adopt.

 

Practical Mathematics in the Drawings of Baldassarre Peruzzi and Antonio Da Sangallo the Younger

Huppert, Ann. “Practical Mathematics in the Drawings of Baldassarre Peruzzi and Antonio Da Sangallo the Younger.” Geometrical Objects, edited by Anthony Gerbino, Springer, 2014, pp. 79–106.

View Publication

Abstract

Combining technical practice with aesthetic intent, Renaissance architecture was by nature a mathematical art. Although the limitations of surviving documents hinder efforts to discern what Italian Renaissance architects knew of mathematics, where they learned it, and how they applied this knowledge, extant drawings from the period offer one means of addressing these questions. Inscribed numerals and calculations, in particular, abound in the drawings by two leading architects of early sixteenth-century Italy, Baldassarre Peruzzi and Antonio da Sangallo the Younger, suggesting that both attained a high degree of numeracy. Comparing these contemporaries is also revealing since, while each incorporated mathematics as a central element in their architectural practice, their approaches diverge in ways that point to and illuminate significant differences in their background and design methods.

Keywords

Mathematical ability; fifteenth century; plumb line; scale line; wooden model

College of Built Environments’ Research Restart Fund Awards Four Grants in Second Cycle

The College of Built Environments launched a funding opportunity for those whose research has been affected by the ongoing pandemic. The Research Restart Fund, with awards up to $5,000, has awarded 4 grants in the second of its two cycles. A grant was awarded to Manish Chalana, faculty member with Urban Design and Planning to help support his efforts to carry out archival research and fieldwork in India for his new book exploring the history and memory of non-dominant groups…