Accurate　prediction　of　Chemical　Oxygen　Demand　(COD)　and　ammonia　nitrogen　(NH3)　is　crucial　for　maintaining　stable　and　effective　wastewater　treatment　processes.　Traditional　methods　rely　on　costly,　high-maintenance　sensors,　limiting　their　application　in　resource-limited　wastewater　treatment　plants.　Soft　sensing　methods　provide　an　alternative　by　reducing　dependence　on　costly　sensors.　However,　existing　approaches　cannot　perform　multitarget　and　multistep　predictions,　limiting　their　practical　applicability.　This　study　introduced　a　novel　triple　attention-enhanced　encoder-decoder　temporal　convolutional　network　(TAED-TCN)　to　address　this　problem.　The　model　used　multimodal　inputs,　including　easily　accessible　water　quality　parameters　and　wastewater　surface　images,　for　multistep　and　synchronous　prediction　of　COD　and　NH3.　When　it　was　validated　with　real-world　sequencing　batch　reactor　wastewater　data,　the　model　demonstrated　superior　multistep　prediction　performance.　Specifically,　the　R2　for　1-h　predictions　of　COD　and　NH3　was　over　26.03　%　and　20.51　%　higher　than　the　baseline　model,　respectively.　By　incorporating　multiple　attention　mechanisms　(feature,　temporal,　and　crossattention),　TAED-TCN　effectively　captured　essential　features,　model　nonlinear　relationships,　and　identified　long-term　dependencies,　thus　enabled　consistent　multitarget　prediction　results　even　under　abnormal　conditions.　Additionally,　economic　analysis　revealed　that　TAED-TCN　could　reduce　COD　and　NH3　monitoring　costs　by　79　%　over　the　equipment　life　cycle.　This　study　offers　a　cost-effective　solution　for　water　quality　prediction,　enhancing　the　operational　efficiency　of　wastewater　management.