Systems, methods, and devices for detecting harmful algal blooms
Described herein are systems, methods, and devices for detecting harmful algae blooms. An example system includes autonomous watercraft; and a computing device operably connected to the autonomous watercraft over a network, the computing device including a processor and a memory having computer-executable instructions stored thereon that cause the processor to: surveil a body of water for an algae growth; receive a local condition at the body of water; predict a spread of the algae growth in the body of water based on the local condition; determine a deployment strategy for the autonomous watercraft based on the spread of the algae growth; and transmit one or more control signals to the plurality of autonomous watercraft based on the deployment strategy, where the autonomous watercraft are configured to collect and analyze a plurality of water samples to determine whether the algae growth is a harmful algae bloom.
1 . An automated system for detecting harmful algae blooms, the system comprising:
a plurality of autonomous watercraft; and
a computing device operably connected to the plurality of autonomous watercraft over a network, the computing device comprising a processor and a memory, the memory having computer-executable instructions stored thereon that, when executed by the processor, cause the processor to:
receive remote imaging data of a body of water;
input the remote imaging data to a trained machine learning model configured to generate a geotagged harmful algal bloom (HAB) probability map;
determine a deployment strategy for the plurality of autonomous watercraft based on the geotagged HAB probability map; and
transmit one or more control signals to the plurality of autonomous watercraft based on the deployment strategy, wherein the plurality of autonomous watercraft are configured to collect and analyze a plurality of water samples to obtain a plurality of temporally and spatially resolved water sample measurements; and
output for display a map overlaying the temporally and spatially resolved water sample measurements and the geotagged HAB probability map.
2 . The system of claim 1 , wherein the one or more control signals are configured to deploy the plurality of autonomous watercraft to a high probability region of the geotagged HAB probability map.
3 . The system of claim 1 , wherein the memory has further computer-executable instructions stored thereon that, when executed by the processor, cause the processor to receive, from the plurality of autonomous watercraft, temporally- and spatially-resolved water sample data.
4 . The system of claim 3 , wherein the memory has further computer-executable instructions stored thereon that, when executed by the processor, cause the processor to overlay the temporally- and spatially-resolved water sample data on a map of the body of water.
5 . The system of claim 1 , wherein one or more of the plurality of autonomous watercraft comprise a sensor configured to detect a harmful algae bloom indicator.
6 . The system of claim 5 , wherein the sensor comprises one or more of a fluorescence-based sensor, a phosphorus detection sensor, a nitrogen detection sensor, a temperature sensor, a salinity sensor, a pH sensor, a dissolved oxygen sensor, an ultrasound sensor, a light detection and ranging (LIDAR) sensor, an imaging sensor, or a photoelectric sensor.
7 . The system of claim 1 , wherein one or more of the plurality of autonomous watercraft comprises a sensor system configured to detect a harmful algae bloom indicator.
8 . The system of claim 7 , wherein the sensor system comprises one or more of a liquid chromatography-mass spectrometry (LC-MS) system or an assay system.
9 . The system of claim 1 , wherein the remote imaging data comprises imaging data from one or more of a satellite, an aircraft, or a drone.
10 . The system of claim 1 , wherein the remote imaging data comprises imaging data captured by one or more of a Sea-viewing Wide Field-of-view Sensor (SeaWiFS), a moderate resolution imaging spectroradiometer (MODIS), an advanced very-high-resolution radiometer (AVHRR), or an airborne visible/infrared spectrometer (AVIRIS).
11 . The system of claim 1 , wherein the step of receive remote imaging data at the body of water comprises receiving weather or water data, the weather or water data comprising one or more of water temperature, water salinity, wind speed and/or direction, or water current speed and/or direction.
12 . The system of claim 1 , wherein the map overlaying the temporally and spatially resolved water sample measurements comprises an ensemble model.
13 . The system of claim 1 , wherein the step of determining the deployment strategy for the plurality of autonomous watercraft comprises using a resource mapping model.
14 . The system of claim 13 , wherein the resource mapping model is a Markov chain model, a Monte Carlo simulation model, a random forest model, a deep learning model, an agent-based model, or an evolutionary model.
15 . The system of claim 1 , further comprising one or more autonomous aerial vehicles (UAVs) operably coupled to the computing device over the network, wherein the one or more UAVs are configured to collect remote imaging data of algae growth and/or collect and analyze the water samples.
16 . A method for detecting harmful algae blooms, the method comprising:
providing a plurality of autonomous watercraft;
receiving remote imaging data of a body of water;
inputting the remote imaging data to a trained machine learning model configured to generate a geotagged harmful algal bloom (HAB) probability map;
deploying the plurality of autonomous watercraft based on a deployment strategy, wherein the deployment strategy is based on the HAB probability map;
collecting, using the plurality of autonomous watercraft, a plurality of water samples to obtain a plurality of temporally and spatially resolved water sample measurements; and
outputting for display a map overlaying the temporally and spatially resolved water sample measurements and HAB probability map.
17 . The method of claim 16 , further comprising receiving, from the plurality of autonomous watercraft, temporally- and spatially-resolved water sample data.
18 . The method of claim 17 , further comprising overlaying the temporally- and spatially-resolved water sample data on a map of the body of water.
19 . The method of claim 16 , wherein the remote imaging data comprises imaging data from one or more of a satellite, an aircraft, or a drone.
20 . The method of claim 16 , wherein the remote imaging data comprises imaging data captured by one or more of a Sea-viewing Wide Field-of-view Sensor (SeaWiFS), a moderate resolution imaging spectroradiometer (MODIS), an advanced very-high-resolution radiometer (AVHRR), or an airborne visible/infrared spectrometer (AVIRIS).
21 . The method of claim 16 , further comprising receiving weather or water data, the weather or water data comprising one or more of water temperature, water salinity, wind speed and/or direction, or water current speed and/or direction and inputting the weather or water data into the trained machine learning model.
22 . The method of claim 16 , wherein the map overlaying the temporally and spatially resolved water sample measurements comprises an ensemble model.
23 . The method of claim 16 , wherein the step of determining the deployment strategy for the plurality of autonomous watercraft comprises using a resource mapping model.
24 . The method of claim 23 , wherein the resource mapping model is a Markov chain model, a Monte Carlo simulation model, a random forest model, a deep learning model, an agent-based model, or an evolutionary model.
25 . A computing system for detecting harmful algae blooms, the system comprising:
a processor; and
a memory operably coupled to the processor, the memory having computer-executable instructions stored thereon that, when executed by the processor, cause the processor to:
receive remote imaging data of a body of water;
input the remote imaging data to a trained machine learning model configured to generate a geotagged harmful algal bloom (HAB) probability map;
determine a deployment strategy for a plurality of autonomous watercraft based on the geotagged harmful algal bloom (HAB) probability map; and
transmit one or more control signals to the plurality of autonomous watercraft based on the deployment strategy, wherein the plurality of autonomous watercraft are configured to collect and analyze a plurality of water samples to obtain a plurality of temporally and spatially resolved water sample measurements; and
output for display a map overlaying the temporally and spatially resolved water sample measurements and HAB probability map.