Abstract: In-situ fluorimeters and methods and systems for collecting and analyzing sensor data to predict water source contamination are provided. In one embodiment, a method is provided that includes receiving sensor data regarding a water source. Changepoints may then be calculated within the sensor data and the sensor data may be split into intervals at the changepoints. A machine learning model may then be used to classify the intervals and a predicted contamination event for the water source may be identified based on the classified intervals. In another embodiment, an in-situ fluorimeter is provided. The in-situ fluorimeter comprises one or more UV LEDs centered around a pre-set excitation wavelength (e.g., a TLF excitation wavelength), a bandpass filter, a lens, a photodiode system, a machine learning platform; and an alarm triggered by contamination events, wherein the alarm is calibrated through the machine learning system.

Abstract: In-situ fluorimeters and methods and systems for collecting and analyzing sensor data to predict water source contamination are provided. In one embodiment, a method is provided that includes receiving sensor data regarding a water source. Changepoints may then be calculated within the sensor data and the sensor data may be split into intervals at the changepoints. A machine learning model may then be used to classify the intervals and a predicted contamination event for the water source may be identified based on the classified intervals. In another embodiment, an in-situ fluorimeter is provided. The in-situ fluorimeter comprises one or more UV LEDs centered around a pre-set excitation wavelength (e.g., a TLF excitation wavelength), a bandpass filter, a lens, a photodiode system, a machine learning platform; and an alarm triggered by contamination events, wherein the alarm is calibrated through the machine learning system.