Systems And Methods For Assessing Crop Damaging Factors Associated With Agronomic Fields
Systems and methods are provided for use in assessing disease threat in a field. An example computer-implemented method includes accessing weather data for a field where the field includes a crop and the weather data includes a weather condition for the field during a time period and identifying multiple intervals within the time period as threat intervals, based on the weather condition of the field during each of the multiple intervals being with a first range. The method also includes aggregating the multiple threat intervals into a damaging factor, based, in part, on ones of the multiple intervals being consecutive intervals during the time period, and comparing the damaging factor to a threat threshold. The method then includes, in response to the damaging factor satisfying the threat threshold, generating and transmitting, by the computing device, an output indicative of the damaging factor.
1 . A computer-implemented method for use in assessing disease threat in a field, the method comprising:
accessing, by a computing device, weather data for a field, the field including a crop and the weather data including a weather condition for the field during a time period, the time period including multiple intervals;
identifying, by the computing device, the multiple intervals within the time period as threat intervals, based on the weather condition of the field during each of the multiple intervals being within a first range;
aggregating, by the computing device, the multiple threat intervals into a damaging factor, based, in part, on ones of the multiple intervals being consecutive intervals during the time period;
comparing the damaging factor to a threat threshold; and
in response to the damaging factor satisfying the threat threshold, generating and transmitting, by the computing device, an output indicative of the damaging factor.
2 . The computer-implemented method of claim 1 , wherein the crop includes corn; and
wherein the time period includes a time period between a first date or first growth stage of the crop and a second date or second growth stage of the crop.
3 . The computer-implemented method of claim 1 , wherein the crop includes corn, soybeans, and/or wheat.
4 . The computer-implemented method of claim 1 , wherein the time period includes one day, two days, fourteen days, or twenty-eight days.
5 . The computer-implemented method of claim 1 , further comprising generating, using a machine learning model, an augmented damaging factor based on the damaging factor and at least one feature related to the crop and/or the field; and
wherein comparing the damaging factor to the threat threshold includes comparing the augmented damaging factor to the threat threshold.
6 . The computer-implemented method of claim 1 , wherein the at least one feature includes a relative maturity of the crop, a susceptibility rating of the crop, a seeding rate of the crop in the field, and an earth observation residue for the field based on satellite images of the field.
7 . The computer-implemented method of claim 1 , further comprising initiating an assessment of a threat to the field for a disease, prior to accessing the weather data, wherein the first range is associated with the disease.
8 . The computer-implemented method of claim 1 , wherein each of the multiple intervals includes an hour; and
wherein identifying the multiple intervals of the time period as threat intervals includes identifying each interval of the multiple intervals within the time period as a threat interval when the weather condition of the field during the interval is within a first range.
9 . The computer-implemented method of claim 1 , wherein the weather condition includes temperature and humidity; and
wherein identifying the multiple intervals as threat intervals is based on:
the temperature of the field during each of the multiple intervals being within the first range; and
the humidity of the field during each of the multiple intervals being within a second range.
10 . The computer-implemented method of claim 9 , wherein the temperature of each interval includes an average temperature during the interval; and
wherein a humidity of each interval includes an average humidity during the interval.
11 . The computer-implemented method of claim 1 , wherein aggregating the threat intervals is based, at least in part, on:
R
(
w
k
)
=
∑
s
k
P
(
L
(
F
(
h
(
x
)
,
t
(
x
)
)
)
)
where F( ) generates a threat interval based on relative humidity, h(x), and temperature, t(x), for a give time point, x, L( ) transforms the threat interval to a length of continuous threat intervals and respective counts, and P( ) weights the length of the group, as summed.
12 . The computer-implemented method of claim 1 , wherein aggregating the multiple intervals includes weighting the consecutive intervals of the multiple intervals more than the individual ones of the multiple intervals.
13 . The computer-implemented method of claim 12 , wherein aggregating the multiple intervals includes weighting the consecutive intervals by a power associated with a number of the consecutive intervals.
14 . The computer-implemented method of claim 1 , wherein the output includes instructions to spray the field; and/or
wherein the method further comprises spraying the field with a treatment, in response to the damaging factor satisfying the threat threshold.
15 . The computer-implemented method of claim 14 , wherein the treatment includes a fungicide.
16 . A system for use in assessing disease threat in a field, the system comprising at least one computing device configured to:
access weather data for a field, the field including a crop and the weather data including a weather condition for the field during a time period, the time period including multiple intervals;
identify the multiple intervals within the time period as threat intervals, based on the weather condition of the field during each of the multiple intervals being within a first range;
aggregate the multiple threat intervals into a damaging factor, based, in part, on ones of the multiple intervals being consecutive intervals during the time period;
compare the damaging factor to a threat threshold; and
in response to the damaging factor satisfying the threat threshold, generate and transmit an output indicative of the damaging factor.
17 . The system of claim 16 , further comprising farm equipment;
wherein the at least one computing device is configured to transmit the output to the farm equipment; and
wherein, in response to receipt of the output, the farm equipment is configured to treat the field to address the disease threat represented by the damaging factor.
18 . The system of claim 16 , wherein the at least one computing device is further configured to:
generate, using a machine learning model, an augmented damaging factor based on the damaging factor and at least one feature related to the crop and/or the field; and
compare the augmented damaging factor to the threat threshold;
wherein the at least one feature includes a relative maturity of the crop, a susceptibility rating of the crop, a seeding rate of the crop in the field, and an earth observation residue for the field based on satellite images of the field.
19 . The system of claim 16 , wherein the at least one computing device is further configured to aggregate the threat intervals based, at least in part, on:
R
(
w
k
)
=
∑
s
k
P
(
L
(
F
(
h
(
x
)
,
t
(
x
)
)
)
)
where F( ) generates a threat interval based on relative humidity, h(x), and temperature, t(x), for a give time point, x, L( ) transforms the threat interval to a length of continuous threat intervals and respective counts, and P( ) weights the length of the group, as summed.
20 . A non-transitory computer-readable storage medium comprising executable instructions for use in assessing disease threat in a field, which when executed by at least one processor, cause the at least one processor to:
access weather data for a field, the field including a crop and the weather data including a weather condition for the field during a time period, the time period including multiple intervals;
identify the multiple intervals within the time period as threat intervals, based on the weather condition of the field during each of the multiple intervals being within a first range;
aggregate the multiple threat intervals into a damaging factor, based, in part, on ones of the multiple intervals being consecutive intervals during the time period;
compare the damaging factor to a threat threshold; and
in response to the damaging factor satisfying the threat threshold, generate and transmit an output indicative of the damaging factor.
21 . The non-transitory computer-readable storage medium of claim 20 , wherein the executable instructions, when executed by the at least one processor, further cause the at least one processor to:
generate, using a machine learning model, an augmented damaging factor based on the damaging factor and at least one feature related to the crop and/or the field; and
compare the augmented damaging factor to the threat threshold;
wherein the at least one feature includes a relative maturity of the crop, a susceptibility rating of the crop, a seeding rate of the crop in the field, and an earth observation residue for the field based on satellite images of the field.