New Article: Predictive models using “cheap and easy” field measurements: Can they fill a gap in FSM?

461 views

  • BJWard
  • BJWard's Avatar
    Topic Author
  • PhD researcher, Eawag/Sandec
  • Posts: 3
  • Likes received: 4

New Article: Predictive models using “cheap and easy” field measurements: Can they fill a gap in FSM?

Dear all,
Lack of access to laboratory analysis is a major barrier to characterization, monitoring, and treatment of faecal sludge. In our new article, our team from Sandec/Eawag and University of Zambia evaluated simple and cost-efficient field predictors of sludge characteristics and dewatering performance, coupled with a range of models. We found that color and texture data extracted from photographs of sludge samples, combined with EC and pH probe readings were adequate predictors of TS, NH4-N, settling efficiency, and filtration time when used as inputs to machine learning models. Whether the sludge came from a pit latrine or a septic tank was also a useful predictor of characteristics and dewatering performance.
Access our article open source at Water Research: https://doi.org/10.1016/j.watres.2021.116997
Access our entire open source dataset of sludge characteristics for 465 samples from Lusaka, Zambia: doi.org/10.25678/00037X

Abstract (added by moderator PCP): 
The characteristics of fecal sludge delivered to treatment plants are highly variable. Adapting treatment process operations accordingly is challenging due to a lack of analytical capacity for characterization and monitoring at many treatment plants. Cost-efficient and simple field measurements such as photographs and probe readings could be proxies for process control parameters that normally require laboratory analysis. To investigate this, we evaluated questionnaire data, expert assessments, and simple analytical measurements for fecal sludge collected from 421 onsite containments. This data served as inputs to models of varying complexity. Random forest and linear regression models were able to predict physical-chemical characteristics including total solids (TS) and ammonium (NH4+-N) concentrations, and solid-liquid separation performance including settling efficiency and filtration time (R2 from 0.51-0.66) based on image analysis of photographs (sludge color, supernatant color, and texture) and probe readings (conductivity (EC) and pH). Supernatant color was the best predictor of settling efficiency and filtration time, EC was the best predictor of NH4+-N, and texture was the best predictor of TS. Predictive models have the potential to be applied for real-time monitoring and process control if a database of measurements is developed and models are validated in other cities. Simple decision tree models based on the single classifier of containment type can also be used to make predictions about citywide planning, where a lower degree of accuracy is required.
The following user(s) like this post: nirupaman09
You need to login to reply
Share this thread:
Recently active users. Who else has been active?
Time to create page: 0.218 seconds