Zac Yung-Chun Liu

Mr. Zac Yung-Chun Liu


Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 March 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
ZLZac Yung-Chun Liu
Zac Yung-Chun Liu
ACAndrew J. Chamberlin
Andrew J. Chamberlin
KTKrti Tallam
Krti Tallam
IJIsabel J. Jones
Isabel J. Jones
LLLance L. Lamore
Lance L. Lamore
GLGiulio De Leo
Giulio De Leo
Schistosomiasis is a debilitating parasitic disease of poverty that affects more than 200 million people worldwide, mostly in sub-Saharan Africa, and is clearly associated with the construction of dams and water resource management infrastructure in tropical and subtropical areas. Changes to hydrology and salinity linked to water infrastructure development may create conditions favorable to the aquatic vegetation that is suitable habitat for the intermediate snail hosts of schistosome parasites. With thousands of small and large water reservoirs, irrigation canals, and dams developed or under construction in Africa, it is crucial to accurately assess the spatial distribution of high-risk environments that are habitat for freshwater snail intermediate hosts of schistosomiasis in rapidly changing ecosystems. Yet, standard techniques for monitoring snails are labor-intensive, time-consuming, and provide information limited to the small areas that can be manually sampled. Consequently, in low-income countries where schistosomiasis control is most needed, there are formidable challenges to identifying potential transmission hotspots for targeted medical and environmental interventions. In this study, we developed a new framework to map the spatial distribution of suitable snail habitat across large spatial scales in the Senegal River Basin by integrating satellite data, high-definition, low-cost drone imagery, and an artificial intelligence (AI)-powered computer vision technique called semantic segmentation. A deep learning model (U-Net) was built to automatically analyze high-resolution satellite imagery to produce segmentation maps of aquatic vegetation, with a fast and robust generalized prediction that proved more accurate than a more commonly used random forest approach. Accurate and up-to-date knowledge of areas at highest risk for disease transmission can increase the effectiveness of control interventions by targeting habitat of disease-carrying snails. With the deployment of this new framework, local governments or health actors might better target environmental interventions to where and when they are most needed in an integrated effort to reach the goal of schistosomiasis elimination.

1 May 2016 in Icarus
Verified
Journal Article
Closed access
ZLZac Yung-Chun Liu
Zac Yung-Chun Liu
JRJani Radebaugh
Jani Radebaugh
RHRon A. Harris
Ron A. Harris
Eric H ChristiansenEric H Christiansen
Eric H Christiansen
CNCatherine D. Neish
Catherine D. Neish
RLRalph Lorenz
Ralph Lorenz

22 February 2013 in Natural Hazards
Verified
Journal Article
Open access
PDF file
ZLZac Yung-Chun Liu
Zac Yung-Chun Liu
RHRon Alan Harris
Ron Alan Harris
Arthur Wichmann’s “Earthquakes of the Indian Archipelago” documents several large earthquakes and tsunami throughout the Banda Arc region that can be interpreted as mega-thrust events. However, the source regions of these events are not known. One of the largest and well-documented events in the catalog is the great earthquake and tsunami affecting the Banda Islands on August 1, 1629. It caused severe damage from a 15-m tsunami that arrived at the Banda Islands about a half hour after violent shaking stopped. The earthquake was also recorded 230 km away in Ambon, but no tsunami is mentioned. This event was followed by at least 9 years of uncommonly frequent seismic activity in the region that tapered off with time, which can be interpreted as aftershocks. The combination of these observations indicates that the earthquake was most likely a mega-thrust event. We use an inverse modeling approach to numerically reconstruct the tsunami, which constrains the likely location and magnitude of the 1629 earthquake. Only, linear numerical models are applied due to the low resolution of bathymetry in the Banda Islands and Ambon. Therefore, we apply various wave amplification factors (1.5–4) derived from simulations of recent, well-constrained tsunami to bracket the upper and lower limits of earthquake moment magnitudes for the event. The closest major earthquake sources to the Banda Islands are the Tanimbar and Seram Troughs of the Banda subduction/collision zone. Other source regions are too far away for such a short arrival time of the tsunami after shaking. Moment magnitudes predicted by the models in order to produce a 15-m tsunami are Mw of 9.8–9.2 on the Tanimbar Trough and Mw 8.8–8.2 on the Seram Trough. The arrival times of these waves are 58 min for Tanimbar Trough and 30 min for Seram Trough. The model also predicts 5-m run-up for Ambon from a Tanimbar Trough source, which is inconsistent with the historical records. Ambon is mostly shielded from a wave generated by a Seram Trough source. We conclude that the most likely source of the 1629 mega-thrust earthquake is the Seram Trough. Only one earthquake >Mw 8.0 is recorded instrumentally from the eastern Indonesia region although high rates of strain (50–80 mm/a) are measured across the Seram section of the Banda subduction zone. Enough strain has already accumulated since the last major historical event to produce an earthquake of similar size to the 1629 event. Due to the rapid population growth in coastal areas in this region, it is imperative that the most vulnerable coastal areas prepare accordingly.

15 July 2021 in Frontiers in Public Health
Verified
Journal Article
Open access
KTKrti Tallam
Krti Tallam
ZLZac Yung-Chun Liu
Zac Yung-Chun Liu
ACAndrew J. Chamberlin
Andrew J. Chamberlin
IJIsabel J. Jones
Isabel J. Jones
PSPretom Shome
Pretom Shome
GLGiulio A. De Leo
Giulio A. De Leo
In recent decades, computer vision has proven remarkably effective in addressing diverse issues in public health, from determining the diagnosis, prognosis, and treatment of diseases in humans to predicting infectious disease outbreaks. Here, we investigate whether convolutional neural networks (CNNs) can also demonstrate effectiveness in classifying the environmental stages of parasites of public health importance and their invertebrate hosts. We used schistosomiasis as a reference model. Schistosomiasis is a debilitating parasitic disease transmitted to humansviasnail intermediate hosts. The parasite affects more than 200 million people in tropical and subtropical regions. We trained our CNN, a feed-forward neural network, on a limited dataset of 5,500 images of snails and 5,100 images of cercariae obtained from schistosomiasis transmission sites in the Senegal River Basin, a region in western Africa that is hyper-endemic for the disease. The image set included both images of two snail genera that are relevant to schistosomiasis transmission – that is,Bulinusspp. andBiomphalaria pfeifferi– as well as snail images that are non-component hosts for human schistosomiasis. Cercariae shed fromBi. pfeifferi and Bulinusspp. snails were classified into 11 categories, of which only two,S. haematobiumandS. mansoni, are major etiological agents of human schistosomiasis. The algorithms, trained on 80% of the snail and parasite dataset, achieved 99% and 91% accuracy for snail and parasite classification, respectively, when used on the hold-out validation dataset – a performance comparable to that of experienced parasitologists. The promising results of this proof-of-concept study suggests that this CNN model, and potentially similar replicable models, have the potential to support the classification of snails and parasite of medical importance. In remote field settings where machine learning algorithms can be deployed on cost-effective and widely used mobile devices, such as smartphones, these models can be a valuable complement to laboratory identification by trained technicians. Future efforts must be dedicated to increasing dataset sizes for model training and validation, as well as testing these algorithms in diverse transmission settings and geographies.

1 May 2016 in Icarus
Verified
Journal Article
Closed access
ZLZac Yung-Chun Liu
Zac Yung-Chun Liu
JRJani Radebaugh
Jani Radebaugh
RHRon A. Harris
Ron A. Harris
Eric H ChristiansenEric H Christiansen
Eric H Christiansen
SRSummer Rupper
Summer Rupper

24 February 2022 in Preprints.org
Verified
Preprint
Open access
PDF file
ZLZac Yung-Chun Liu
Zac Yung-Chun Liu
ACAndrew J. Chamberlin
Andrew J. Chamberlin
KTKrti Tallam
Krti Tallam
IJIsabel J. Jones
Isabel J. Jones
LLLance L. Lamore
Lance L. Lamore
GLGiulio De Leo
Giulio De Leo
Schistosomiasis is a debilitating parasitic disease of poverty that affects more than 200 million people worldwide, mostly in sub-Saharan Africa, and is clearly associated with the construction of dams and water resource management infrastructure in tropical and subtropical areas. Changes to hydrology and salinity linked to water infrastructure development may create conditions favorable to the aquatic vegetation that is suitable habitat for the intermediate snail hosts of schistosome parasites. With thousands of small and large water reservoirs, irrigation canals, and dams developed or under construction in Africa, it is crucial to accurately assess the spatial distribution of high-risk environments that are habitat for freshwater snail intermediate hosts of schistosomiasis in rapidly changing ecosystems. Yet, standard techniques for monitoring snails are labor-intensive, time-consuming, and provide information limited to the small areas that can be manually sampled. Consequently, in low-income countries where schistosomiasis control is most needed, there are formidable challenges to identify potential transmission hotspots for targeted medical and environmental interventions. In this study, we developed a new framework to map the spatial distribution of suitable snail habitat across large spatial scales in the Senegal River Basin by integrating satellite data, high-definition, low-cost drone imagery, and an artificial intelligence (AI)-powered computer vision technique called semantic segmentation. A deep learning model (U-Net) was built to automatically analyze high-resolution satellite imagery to produce segmentation maps of aquatic vegetation, with a fast and robust generalized prediction that proved more accurate than a more commonly used random forest approach. Accurate and up-to-date knowledge of areas at highest risk for disease transmission can increase the effectiveness of control interventions by targeting habitat of disease-carrying snails. With the deployment of this new framework, local governments or health actors might better target environmental interventions to where and when they are most needed in an integrated effort to reach the goal of schistosomiasis elimination.