{"id":3462,"date":"2026-02-21T11:12:59","date_gmt":"2026-02-21T10:12:59","guid":{"rendered":"https:\/\/neuraldesigner.com\/learning\/aquatic-toxicity\/"},"modified":"2026-04-22T13:59:27","modified_gmt":"2026-04-22T11:59:27","slug":"aquatic-toxicity","status":"publish","type":"learning","link":"https:\/\/www.neuraldesigner.com\/learning\/examples\/aquatic-toxicity\/","title":{"rendered":"Model water toxicity using machine learning"},"content":{"rendered":"\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

In this example, we build a machine learning model to calculate water toxicity using actual data from a water body.<\/p><\/section>

Many chemicals partition in water and can exert adverse effects on aquatic systems, threatening the survival of the members of these ecosystems. Calculating a standard measure of aquatic toxicity is a lengthy and costly procedure. As a result, we do not need to measure it in the laboratory.<\/section>

Contents<\/h3>
  1. Application type<\/a><\/li>
  2. Data set<\/a><\/li>
  3. Neural network<\/a><\/li>
  4. Training strategy<\/a><\/li>
  5. Model selection<\/a><\/li>
  6. Testing analysis<\/a><\/li>
  7. Model deployment<\/a><\/li><\/ol>

    \u00a0<\/p>

    This example is solved with Neural Designer<\/a>. You can use the\u00a0free trial<\/a> to understand how the solution is achieved step by step.<\/p><\/section>

    1. Application type<\/h2>

    This is an approximation<\/a>\u00a0project since the variable to be predicted is continuous.<\/p>

    The fundamental goal here is to model the LC50 (the standard measure of toxicity) as a function of the sample’s molecular properties.<\/p><\/section>

    2. Data set<\/h2>

    The first step is to prepare the\u00a0data set<\/a>. This is the source of information for the approximation problem. It is composed of:<\/p>