Vehicle-based anomaly detection using artificial intelligence and combined environmental and geophysical sensor data
Geophysical anomalies in an area or region can be detected, characterized, or otherwise mapped using a combination of environmental and geophysical sensor data acquired using a vehicle, which may be a remotely operated or autonomously controlled unmanned vehicle. Anomalies are detected by processing the environmental sensor data and geophysical sensor data using artificial intelligence algorithms, programs, or models. As an example, the artificial intelligence algorithms, programs, or models can include machine learning algorithms, programs, or models. The environmental sensor data are processed to generate control parameters for controlling the acquisition and/or processing of the geophysical sensor data optimized for environmental conditions in the area.
1 . A method for producing a map depicting geophysical anomalies in an area based on geophysical sensor data, the method comprising:
(a) accessing environmental sensor data with a computer system, the environmental sensor data being indicative of environmental conditions in an area;
(b) accessing a first machine learning algorithm with the computer system, wherein the first machine learning algorithm has been trained on first training data to determine confidence weights from environmental conditions;
(c) generating confidence weight values by applying the environmental sensor data to the first machine learning algorithm, generating a first output as the confidence weight values;
(d) accessing geophysical sensor data with a computer system, the geophysical sensor data being indicative of data acquired from the area using a plurality of different geophysical sensors;
(e) accessing a second machine learning algorithm with the computer system, wherein the second machine learning algorithm has been trained on second training data to identify anomalies in the area from the geophysical sensor data acquired from the area;
(f) generating anomaly map data by applying the geophysical sensor data to the second machine learning algorithm and using the confidence weight values as an input to the second machine learning algorithm to control contributions of different ones of the geophysical sensors when generating the anomaly map data, generating a second output as the anomaly map data; and
(g) providing the anomaly map data to a user, wherein the anomaly map data comprise an anomaly map depicting at least one anomaly in the area.
2 . The method of claim 1 , wherein the accessing the environmental sensor data comprises acquiring the environmental sensor data using environmental sensors coupled to a vehicle.
3 . The method of claim 1 , wherein the accessing the geophysical sensor data comprises acquiring the geophysical sensor data using the plurality of different geophysical sensors.
4 . The method of claim 1 , wherein the first machine learning algorithm is a neural network.
5 . The method of claim 1 , wherein the second machine learning algorithm is a neural network and the using the confidence weight values as an input to the second machine learning algorithm comprises applying the confidence weight values to hidden layers of the neural network.
6 . The method of claim 1 , wherein the environmental sensor data comprise at least one of soil moisture data, soil temperature data, air moisture data, air temperature data, or albedo.
7 . The method of claim 1 , wherein the geophysical sensor data comprise at least one of ground penetrating radar data, magnetometer data, optical instrumentation data, X-ray spectral data, optical spectral data, hyperspectral data, nuclear magnetic resonance data, acoustic data, or accelerometer data.
8 . The method of claim 7 , wherein the optical instrumentation data comprise at least one of visible spectrum camera data, infrared camera data, or ultraviolet camera data.
9 . The method of claim 1 , wherein the anomaly map depicts a location of the at least one anomaly.
10 . The method of claim 9 , wherein the anomaly map depicts a probability of the location of the at least one anomaly.
11 . The method of claim 1 , wherein the at least one anomaly comprises an unexploded ordnance.
12 . The method of claim 1 , wherein the at least one anomaly comprises a mineral deposit.
13 . The method of claim 12 , wherein the anomaly map further comprises a mineral deposit layer indicating a type of a mineral in the mineral deposit.
14 . The method of claim 13 , wherein the type of the mineral is determined based on the geophysical sensor data that comprise at least one of X-ray spectral data, optical spectral data, hyperspectral data, or nuclear magnetic resonance data.
15 . The method of claim 1 , wherein the at least one anomaly comprises a civil engineering survey object.
16 . The method of claim 15 , wherein the civil engineering survey object includes at least one of an electrical utility, a gas utility, a water utility, a waste tank, a sewer, or a tunnel.
17 . The method of claim 1 , wherein the at least one anomaly comprises a geophysical feature.
18 . The method of claim 17 , wherein the geophysical feature includes at least one of a lava tube, a cave, or a hydrologic resource.
19 . A method for generating an anomaly map depicting geophysical anomalies in an area, the method comprising:
(a) acquiring environmental sensor data using environmental sensors coupled to a vehicle;
(b) processing the environmental sensor data using an electronic processor housed on the vehicle to generate geophysical sensing control parameter data for controlling a geophysical sensing mode of the vehicle;
(c) acquiring geophysical sensor data using geophysical sensors coupled to the vehicle while in the geophysical sensing mode; and
(d) processing the geophysical sensor data using the electronic processor to generate an anomaly map that depicts at least one anomaly within the area.
20 . The method of claim 19 , wherein the environmental sensor data are processed by the electronic processor by inputting the environmental sensor data to a machine learning algorithm, generating an output as the geophysical sensing control parameter data.
21 . The method of claim 20 , wherein the machine learning algorithm comprises a neural network.
22 . The method of claim 19 , wherein the geophysical sensor data are processed by the electronic processor by inputting the geophysical sensor data to a machine learning algorithm, generating an output as the anomaly map.
23 . The method of claim 22 , wherein the machine learning algorithm comprises a neural network.
24 . The method of claim 23 , wherein the geophysical sensing control parameter data comprise confidence weight values that are input to hidden layers of the neural network by the electronic processor to weigh different geophysical sensor data types based on environmental conditions in the area as measured by the environmental sensors.
25 . The method of claim 19 , wherein the geophysical sensing control parameter data are processed by the electronic processor to control an operation of the vehicle when the vehicle is in the geophysical sensing mode.
26 . The method of claim 25 , wherein the vehicle is an aerial vehicle and processing the geophysical sensing control parameter data by the electronic processor controls the operation of the aerial vehicle based on the environmental conditions in the area and on which the geophysical sensors are being used to acquire the geophysical sensor data.
27 . The method of claim 25 , wherein processing the geophysical sensing control parameter data by the electronic processor controls the operation of the geophysical sensors such that different ones of the geophysical sensors are operated to acquire the geophysical sensor data based on the environmental conditions in the area.
28 . The method of claim 19 , wherein the anomaly map depicts a location of the at least one anomaly.
29 . The method of claim 28 , wherein the anomaly map depicts a probability of the location of the at least one anomaly.
30 . A vehicle-based system for mapping geophysical anomalies within an area, the vehicle-based system comprising:
a vehicle;
a plurality of environmental sensors coupled to the vehicle;
a plurality of geophysical sensors coupled to the vehicle; and
an electronic processor housed within the vehicle and in communication with the plurality of environmental sensors and the plurality of geophysical sensors, the electronic processor being configured to:
acquire environmental sensor data with the plurality of environmental sensors;
acquire geophysical sensor data with the plurality of geophysical sensors; and
generate an anomaly map that depicts at least one anomaly within an area using the environmental sensor data and the geophysical sensor data.
31 . The vehicle-based system of claim 30 , wherein the electronic processor is configured to generate the anomaly map by:
accessing a first neural network;
inputting the environmental sensor data to the first neural network, generating output as confidence weight values for hidden layers in a second neural network;
accessing the second neural network; and
inputting the confidence weight values and the geophysical sensor data to the second neural network, generating output as the anomaly map.
32 . The vehicle-based system of claim 30 , wherein the vehicle is an aerial vehicle.
33 . The vehicle-based system of claim 32 , wherein the aerial vehicle is an unmanned aerial vehicle (UAV).
34 . The vehicle-based system of claim 33 , wherein the UAV is an autonomously controlled UAV.
35 . The vehicle-based system of claim 30 , wherein the vehicle is a ground-based vehicle.
36 . The vehicle-based system of claim 35 , wherein the ground-based vehicle is an unmanned ground vehicle (UGV).
37 . The vehicle-based system of claim 36 , wherein the UGV is an autonomously controlled UGV.
38 . The vehicle-based system of claim 30 , wherein the vehicle comprises a trailer that is coupled to another vehicle.
39 . The vehicle-based system of claim 38 , wherein the trailer is fabricated from at least one of non-ferromagnetic materials or non-metallic materials.
40 . The vehicle-based system of claim 30 , wherein the environmental sensors comprise at least one of a soil moisture sensor, a soil temperature sensor, an air moisture sensor, an air temperature sensor, or an albedometer; and further wherein the environmental sensor data comprises information regarding environmental conditions in the area which is utilized by the electronic processor to control operation of the geophysical sensors such that different ones of the geophysical sensors are operated to acquire the geophysical sensor data based on the environmental conditions in the area.
41 . The vehicle-based system of claim 40 , wherein the geophysical sensors comprise at least one of a ground penetrating radar sensor, a magnetometer, a metal detecting excitation coil, a metal detecting sensing coil, an optical instrumentation sensor, an X-ray spectral sensor, an optical spectral sensor, a hyperspectral sensor, an acoustic sensor, a nuclear magnetic resonance sensor, or an inertial sensor.
42 . The vehicle-based system of claim 41 , wherein the magnetometer comprises at least one of a 3-component fluxgate magnetometer or a magnetometer array.
43 . The vehicle-based system of claim 41 , wherein the optical instrumentation sensor comprises at least one of a visible spectrum camera, an infrared camera, or an ultraviolet camera.