| 1. |
- Hoffmann, Sabine, et al.
(författare)
-
A Research Agenda for the Future of Urban Water Management : Exploring the Potential of Nongrid, Small-Grid, and Hybrid Solutions
- 2020
-
Ingår i: Environmental Science and Technology. - : American Chemical Society (ACS). - 0013-936X .- 1520-5851. ; 54:9, s. 5312-5322
-
Forskningsöversikt (refereegranskat)abstract
- Recent developments in high- and middle-income countries have exhibited a shift from conventional urban water systems to alternative solutions that are more diverse in source separation, decentralization, and modularization. These solutions include nongrid, small-grid, and hybrid systems to address such pressing global challenges as climate change, eutrophication, and rapid urbanization. They close loops, recover valuable resources, and adapt quickly to changing boundary conditions such as population size. Moving to such alternative solutions requires both technical and social innovations to coevolve over time into integrated socio-technical urban water systems. Current implementations of alternative systems in high- and middle-income countries are promising, but they also underline the need for research questions to be addressed from technical, social, and transformative perspectives. Future research should pursue a transdisciplinary research approach to generating evidence through socio-technical "lighthouse" projects that apply alternative urban water systems at scale. Such research should leverage experiences from these projects in diverse socio-economic contexts, identify their potentials and limitations from an integrated perspective, and share their successes and failures across the urban water sector.
|
|
| 2. |
- Russo, Stefania, et al.
(författare)
-
The value of human data annotation for machine learning based anomaly detection in environmental systems
- 2021
-
Ingår i: Water Research. - : Elsevier BV. - 0043-1354. ; 206
-
Tidskriftsartikel (refereegranskat)abstract
- Anomaly detection is the process of identifying unexpected data samples in datasets. Automated anomaly detection is either performed using supervised machine learning models, which require a labelled dataset for their calibration, or unsupervised models, which do not require labels. While academic research has produced a vast array of tools and machine learning models for automated anomaly detection, the research community focused on environmental systems still lacks a comparative analysis that is simultaneously comprehensive, objective, and systematic. This knowledge gap is addressed for the first time in this study, where 15 different supervised and unsupervised anomaly detection models are evaluated on 5 different environmental datasets from engineered and natural aquatic systems. To this end, anomaly detection performance, labelling efforts, as well as the impact of model and algorithm tuning are taken into account. As a result, our analysis reveals the relative strengths and weaknesses of the different approaches in an objective manner without bias for any particular paradigm in machine learning. Most importantly, our results show that expert-based data annotation is extremely valuable for anomaly detection based on machine learning.
|
|
