摘要：Resource recovery through reuse of by-products of the sanitation chain presents a great potential towards ensuring universal access to safely managed sanitation. Many developing countries are faced with uncertainty over public and environmental health concerns associated with use of faecal sludge in agriculture. Due to resource constraints, limited data exists on the characteristics of faecal sludge to inform proper and safe use in agriculture. Despite predictive characterisation being demonstrated to be a resource-efficient approach to generate data in other fields, its application in agricultural resource recovery from faecal sludge is lacking in the literature. This paper explored predictive modelling as a less resource-intensive approach for characterisation of nutrients and pathogens in faecal sludge. Specifically, it investigated the extent to which gravimetric parameters could predict nutrients and pathogens in pit latrine sludge from informal settlements in the cities of Malawi. The study explored predictive models to estimate total ammoniacal nitrogen (TAN), total phosphorus (TP), <i>E.coli</i> and helminth eggs from gravimetric parameters (total solids [TS] and total volatile solids [TVS]) in pit latrine sludge. The models developed in the study allow substantially reliable estimation of TAN (R<sup>2</sup><sub>pred</sub> = 75.4%) and TP (R<sup>2</sup><sub>pred</sub> = 78.2%); they also provide moderately reliable predictions for <i>E.coli</i> (R<sup>2</sup><sub>pred</sub> = 69.1%) and helminth eggs (R<sup>2</sup><sub>pred</sub> = 74.3%) from total solids. Since total solids are easy and inexpensive to measure, the models present an option that can reduce resource requirement for characterisation of pit latrine sludge for informed decision-making when using pit latrine sludge in agriculture. In the absence of data on faecal sludge characteristics at the national level, the models provide a starting point for estimation of pathogens and nutrients in sludge for agricultural use. However, stepwise refinement of the models needs to be done through their validation for different types of sludge and inclusion of spatially available demographic, technical and environmental (SPA-DET) data.
