Non-Traditional Indicators
Use of massive computational power to harness non-traditional data from sensors, signals, and satellite imagery is also showing their potential for continuous monitoring of the lives and environments of the localities. This page presents our ongoing research on non-traditional data sources to create indicators for electricity consumption, land use, connectivity, and pollution from nontraditional sources.
Electricity Consumption (Nighttime lights)
Analyzing the state and growth of various socio-economic indicators is essential for effective developmental planning at a sub-national level. However, in many cases, data regarding such indicators are not publicly available and/or hard to collect. In many other cases, the available data may not be recent enough. In contrast, satellite data is both readily available and up-to-date. In recent times, various studies have been conducted to use different types of satellite data as a proxy to determine the condition of socio-economic indicators in different places around the world. In this paper, we study the efficacy of one such data source, nighttime lights (NTL), for monitoring factors related to sustainable development in the context of Bangladesh.
Publications:
M. Wahed, R. A. Rizvee, R. R. Haque, A. M. Ali, M. Zaber and A. A. Ali, “What Can Nighttime Lights Tell Us about Bangladesh?” in IEEE Region 10 Symposium (TENSYMP), Dhaka, 2020.
Land Use and Land Cover
With advent of high definition satellite images, high resolution data, novel computational methods such as deep neural network analysis, and hardware capable of high-speed analysis- urban planning is seeing a paradigm shift. Legacy data on urban environments are now being complemented with high-volume, high-frequency data. However, the first step of understanding urban space lies in useful categorization of the space that is usable for data collection, analysis and visualization. In this paper we propose a novel categorization method that is readily usable for machine analysis and show applicability of the methodology on a developing world setting.
Categorization to plan sustainable urban spaces should encompass the buildings and their surroundings. However, the state-of-the-art is mostly dominated by classification of building structures, building types etc and largely represents the developed world. Hence, these methods and models are not sufficient for developing countries such as Bangladesh where the surrounding environment is crucial for the categorization. Moreover, these categorizations propose small-scale classifications, which give limited information, have poor scalability, and are slow to compute in real time.
Our proposed method is divided into two steps-categorization and automation. We categorize the urban area in terms of informal and formal spaces and take the surrounding environment into account. 50km × 50km Google Earth image of Dhaka, Bangladesh was visually annotated and categorized by an expert and consequently a map was drawn. The categorization is based broadly on two dimensions-the state of urbanization and the architectural form of urban environment. Consequently, the urban space is divided into four categories: a) highly informal area; 2) moderately informal area; 3) moderately formal area; and 4) highly formal area. In total sixteen sub-categories were identified.
For semantic segmentation and automatic categorization, Google’s deep labV3 plus model was used. The model uses Atrous convolution operation to analyze different layers of texture and shape. This allows us to enlarge the field of view of the filters to incorporate larger context. Image encompassing 70% of the urban space was used to train the model and the remaining 30% was used for testing and validation. The model is able to segment with 75% accuracy and 0.60 Mean Intersection over Union (mIoU)
Publications:
Qianwei Cheng, A K M M Rahman, Anis Sarker, Abu Bakar Siddik Nayem, Ovi Paul, Amin Ahsan Ali, Ryosuke Shibasaki, Moinul Zaber, “Deep-Learning Coupled with Novel Categorization Method to Classify the Urban Environment of the Developing World” has been accepted for “, ICRSETE 2020: International Conference on Remote Sensing, Environment and Transportation Engineering, Paris, France, 2020
Connectivity (Inland Water Ports)
A well-structured inland waterways system should help Bangladesh fulfill SDG goals. In this study, we employ complex network analysis methods to analyze the river-port network of the country. We ascertain different types of ports based on their importance and placement in the connectivity network. Data regarding port location, vessel routes, and schedules were collected from governmental resources. Using the data, a connectivity network was built for further analysis. Different measures of network analysis are used to categorize the ports and the network model has been identified. These categories should help transportation planners and policymakers to better design the inland waterways network of Bangladesh
F. Tabassum, H. Islam, A. A. Ali and M. Zaber, “A Complex Network Analysis of Inland Waterways Port Connectivity of Bangladesh” in IEEE Region 10 Symposium (TENSYMP), Dhaka, 2020.
Air Quality (PM2.5 concentrations)
Particulate matters having diameters of 2.5 um or less (PM2.5) can travel deep into our respiratory tracts, lungs and blood streams and have been linked with health issues worldwide. Such particles have accounted for 123,000 deaths in Bangladesh in 2017. In this paper, we analyze and identify seasonal, hourly, and regional patterns in the propagation of PM2.5 materials in Bangladesh from 2017 to 2019 using the Berkeley dataset. We observe that the concentration of PM2.5 particles has a nationwide median value of about 50 ug/m3, which is unhealthy for sensitive individuals. The concentration varies with season. We observe that the concentrations of PM2.5 in the air is around five times more in winter than in summer. The air quality inside Dhaka is significantly worse. We also observe hourly patterns in how the air quality fluctuates depending on the hour of the day. Using cross correlation analysis, we observed how spikes in PM2.5 concentration levels in one zone may correspond with increased concentrations in a different zone a few hours later, indicating that air currents may cause the particles to move in certain directions. Our exploratory analysis serves as the first cross-country data centric study of the state and propagation patterns of PM2.5 particles within Bangladesh and our findings can serve as foundation for further research on the topic.