Howard County Conservancy Report
2026-11-06
Site Description
Catchment: The Howard County Conservancy is a nonprofit land trust and environmental education center that protects and manages conservation land in Howard County.
(39°18’52”N, 76°52’24”W), draining 0.9 square miles of agricultural conservation land at the Howard County Conservancy. The headwaters originate at the edge of a meadow in a marshy area where skunk cabbage is abundant in spring and summer.
Sensor Deployment: Three in-stream sensors were deployed at Downstream, Midstream, and Upstream positions, with a fourth Air sensor mounted as a dry atmospheric reference. The Downstream position showed active flow. Midstream was fully submerged within a ravine and surrounded by a developed riparian zone. The Upstream position exhibited a wetland populated with skunk cabbage, with the sensor near surface water level.
Goal: To document flow patterns in this watershed and assess whether low-cost thermal sensing is a viable approach for detecting subsurface flow activity and flow permanence.
Study Area Map
Figure 1: Study area map of Howard County Run, Howard County, Maryland. Sensor points indicate the locations of the Upstream, Midstream, and Downstream in-stream temperature loggers deployed along the longitudinal transect. The inset map shows the location of Howard County Run relative to all study sites within the Baltimore County area.
Figure 2: Daily precipitation recorded at the Mount Washington 0.5 N rain gauge (NOAA station US1MDBC0003) from June 2025 through October 2026. Each point shows the total rainfall for one day in inches.
Figure 3: Stacked bar chart showing the proportion of days classified as wet (blue), dry (red), and uncertain (gray) for each sensor position at Howard County Run across the full study period.
Figure 4: Daily wetness state classifications for all sensor positions at Howard County Run from July 2025 through October 2026. Each row represents a sensor position (Air, Downstream, Midstream, Upstream) and each column represents a single day. Blue indicates wet, red indicates dry, and gray indicates uncertain classifications.
Sensor Images
06/26/25
Figure 5: The first deployment, in June 2025, in
midsummer. All positions had surface flow. Riparian cover surrounded
each position, and Midstream had the least flow.
09/10/25
Figure 6: September 2025 deployment. Riparian cover is
still abundant and streamflow is consistent.
01/16/26
Figure 7: January 2026 deployment. Most riparian cover has died back. Upstream is marshy with slushy soil. Midstream is covered with leaves, but the soil is moist. Downstream has moderate flow despite the cold.
03/04/26
Figure 8: March 2026 deployment, early spring. All
stream sensors show flow, consistent with groundwater recharge.
05/21/26
Figure 9: May 2026 deployment, late spring. Downstream
has the most flow. Flow at Upstream is hard to see under tall grass and
skunk cabbage, but it was present. Midstream has consistent flow.
07/20/26
Figure 10: July 2026 deployment. All stream positions
exhibit wetness on a longitudinal gradient.
10/01/26
Figure 11: October 2026, final retrieval. Surface flow
persists at all locations.
Thermal Overview Plots
Figure 12: Temperature recorded every 15 minutes by all four sensors from June 2025 to October 2026. The Air sensor reflects ambient atmospheric conditions, while the three in-stream sensors reflect channel thermal conditions at each longitudinal position. In-stream water temperatures begin in the High 60s°F in summer before declining toward freezing by January, while the Air sensor exhibits considerably larger diurnal swings throughout the monitoring period.
Figure 13: Daily mean temperature for all four sensors at Senior Run from June 2025 to October 2026. Averaging hourly readings to a daily mean smooths short-term fluctuations and reveals seasonal temperature trends across the monitoring period. Convergence between Air and stream sensor temperatures may reflect overcast, cool, or rainy conditions suppressing diurnal contrast rather than reduced surface water presence.
Case studies
Purpose: To illustrate sensor response during different atmospheric and seasonal conditions. Each case study presents a four-panel diagnostic plot followed by a dryness score table for a single selected day.
4-Panel Plots: A four-panel diagnostic figure showing each sensor’s thermal behavior over a 24-hour period.
Panel 1 shows raw temperature readings.
Panel 2 shows temperature rise above each sensor’s morning minimum.
Panel 3 shows the rate of temperature change per minute.
Panel 4 shows the computed dryness score for each sensor. Scores near 0 indicate wet conditions, scores near 1 indicate dry conditions.
Dryness Score table: A summary of each sensor’s thermal classification for the selected day.
The thermal classifier scores each sensor-day from 0 to 1, where 0 indicates wet conditions and 1 indicates dry conditions. The score increases as conditions become drier.
Warming score and cooling score reflect thermal response during the morning and afternoon phases respectively.
Daily score is the average of both.
A conflict flag indicates the two phases produced contradictory results.
Dryness state is the final classification — wet, dry, or uncertain.
August 14th, 2025 (Summer rainfall day)
Figure 14: Four-panel diagnostic plot for August 14th, 2025. Temperatures ranged from 73–90°F with 1.06 inches of rainfall. The Air sensor showed the biggest increase on the morning of the precipitation event and then abruptly cooled. This abrupt cooling period marked the peak of the heavy-rain thunderstorm. The atmospheric temperature decreased by 10 degrees over 20 minutes, which seems to be reflected in the air sensor. Along with this, all in-stream sensors remained thermally stable and were classified as wet throughout the day.
| Sensor | warming_score | cooling_score | daily_score | conflict_flag | dryness_state |
|---|---|---|---|---|---|
| Air | 1.0000 | 1.0000 | 1.0000 | FALSE | dry |
| Downstream | 0.0011 | 0.0002 | 0.0006 | FALSE | wet |
| Midstream | 0.0000 | 0.0000 | 0.0000 | FALSE | wet |
| Upstream | 0.0011 | 0.1431 | 0.0721 | FALSE | wet |
Table 1: A summary of August 14th’s sensor’s thermal classification. No conflict flags were triggered on this day. As expected, all in-stream sensors showed very low daily scores, indicating wetness during this precipitation event
July 27th, 2026 (Normal summer day)
Figure 15: Four-panel diagnostic plot for July 27th, 2025. Temperatures ranged from 68–88°F with wind gusts up to 9 mph. Streams are moving with expected flow patterns with dampened temperature patterns compared to the air sensor.
| Sensor | warming_score | cooling_score | daily_score | conflict_flag | dryness_state |
|---|---|---|---|---|---|
| Air | 1e+00 | 1e+00 | 1e+00 | FALSE | dry |
| Downstream | 0e+00 | 0e+00 | 0e+00 | FALSE | wet |
| Midstream | 0e+00 | 0e+00 | 0e+00 | FALSE | wet |
| Upstream | 6e-04 | 6e-04 | 6e-04 | FALSE | wet |
Table 2: A summary of July 27th sensor’s thermal classification. No conflict flags were detected. Instream sensors had 0s for their daily scores and were categorized as wet, and the air sensor was categorized as dry.
January 25th, 2026 (Precipitated winter day)
Figure 16: Four-panel diagnostic plot for January 25th, 2026. Temperatures ranged from 15 to 25°F, with 3.37 inches of snow and sleet accumulating. The Air sensor stayed between roughly 14 and 21°F, while the Midstream and Upstream sensors remained flat near 32°F throughout the day. The Downstream sensor began warming in the afternoon, rising from about 33°F to about 42°F and holding there overnight while Air cooled, a pattern that cannot be explained by atmospheric forcing.
| Sensor | warming_score | cooling_score | daily_score | conflict_flag | dryness_state |
|---|---|---|---|---|---|
| Air | 1.0000 | 1 | 1.000 | FALSE | dry |
| Downstream | 0.9939 | 0 | 0.497 | TRUE | uncertain |
| Midstream | 0.0000 | 0 | 0.000 | FALSE | wet |
| Upstream | 0.0000 | 0 | 0.000 | FALSE | wet |
Table 3: Dryness scores for January 25th, 2026. Air scored 1.0 and was classified as dry. Midstream and Upstream both scored 0 and were classified as wet. Downstream scored 0.497 and was classified as uncertain, and it triggered a conflict flag because its warming score of 0.9939 disagreed with its cooling score of 0. Its afternoon warming resembled the Air sensor’s response but was most likely caused by a change in the water around the sensor rather than dry conditions.
December 10th, 2025 (Normal winter day) Close-up
Figure 17: Four-panel diagnostic plot for December 10th, 2025. Temperatures ranged from 30–45°F with overcast skies and wind gusts of 13 mph. All three stream sensors were classified as wet, with no conflict flags. The Air sensor rose approximately 20°F above its morning minimum, while the stream sensors rose only 5-7°F. This clearly demonstrates how in-stream water temperatures remain stable even as atmospheric temperatures fluctuate under winter conditions.
| Sensor | warming_score | cooling_score | daily_score | conflict_flag | dryness_state |
|---|---|---|---|---|---|
| Air | 1.0000 | 1e+00 | 1.0000 | FALSE | dry |
| Downstream | 0.3335 | 0e+00 | 0.1667 | FALSE | wet |
| Midstream | 0.0000 | 0e+00 | 0.0000 | FALSE | wet |
| Upstream | 0.3338 | 4e-04 | 0.1671 | FALSE | wet |
Table 4: All three stream sensors classified wet with no conflict flags. Midstream and downstream exhibit only a slight warming score. Air scored 1.0 because its diurnal temperature swing remained responsive to the atmosphere while the stream sensors stayed thermally regulated by water.
Analysis
Over the course of the study, Howard County Conservancy maintained consistent surface flow at its Midstream and downstream locations, with the two sensors categorized as wet on 92.0% and 84.7% of days. The upstream location was wet on 74.5% of days and was both the driest position (8.0% dry days) and the least certain (17.5% uncertain days). The overall daily dryness heat map shows this pattern, with the upstream row carrying most of the dry and uncertain days. This is consistent with a headwater stream, where the upper reach responds more to atmospheric conditions and varying water availability, while the lower channel holds water more reliably. Dry and uncertain days at Upstream were most frequent in July and August in both 2025 and 2026, suggesting seasonal drying at the sampled position, although this cannot be generalized to the whole stream.