Progress 02/15/22 to 02/14/23
Outputs
Target Audience:Our team has foster relationships with the team of the NSF's GA Coastal Ecosystem Long Term Ecological Research (GCELTER) project and coordinated our efforts with GCE-LTER's ongoing long-term data collection programs to augment and expand our field data. We also participated in the Georgia Coastal Research Council meeting to network with other in-state researchers. We also have contacted with Georgia Department of Transportation (Natural Resources Division) that is interested in coastal restoration to strategize the dissemination of project information. ? Changes/Problems:The field data collection continued to suffer in the wake of the COVID-19 pandemic. Although the research team has remained prepared for field works, some delays and no cost extension (NCE) for USDA-NIFA's approval is acticipated. The research team will submit a NCE request in Fall 2023. What opportunities for training and professional development has the project provided?ENGR 8990 Statistical Learning and Data Mining in Engineering was offered in 2022as part of the project products. How have the results been disseminated to communities of interest?We reached out to several scientific communities during this reporting period. It includes, but not limited to, science communities at NSF second Principal Investigators Workshop for Signals in the Soil (SitS) May 2022, Harpenden, UK; NSF Critical Zone Research Network Workshop, July 2022, Golden, CO; American Association of Geographers, Feb 2022, Virtual; NSF 2022 All Scientists' Meeting LTER (long term ecological research), Aug 2022, Pacific Grove, CA; GCE (Georgia Coastal Ecosystem) LTER Annual Meeting; Jan 2023, Athens, GA. We also reached out to Bayer through Grants4Tech Carbon stock 2022 Challenge. What do you plan to do during the next reporting period to accomplish the goals?The developed sensing plat form will be installed in the field and the field data will be collected. Based on the collected data from the sensing platform in the field, the relationship among the soils properties, SOC, and remote sensing datawill be investigated along with the depth of salt marsh soils.
Impacts
What was accomplished under these goals?
Lab Sensor Calibration: We tested the low-cost sensors in the lab with simulated scenarios, test solutions, and in the field. Low-cost sensors were also compared with Hanna HI9298194 Multiparameter meter for performance.We calibrated and tested the low-cost sensors in simulated and field conditions. Data collected: Field trips and Samples collected at below threelocations and atotal of 197 data points were collected, with data mentioned above over six field trips. At Sapelo Island, data were collected from Dean Creek marsh and Airport Marsh around different times of year (March, Sept, and December, 2022) Skidway Island was collected from two sites in November 2022 South Newport marsh near public pier data was collected in December 2022 To test the predictability of soil properties collected by low-cost sensors, we collected data from our three salt marsh sites, Sapelo Island, South Newport, and Skidway Island. During the field tests, below soils properties and other field data were collected: Soil Properties: Soil pH, Soil Temperature, Redox Potential, Soil Salinity, Soil electrical conductivity, Hanna HI9298194 Multiparameter meter Color Data: Nix color sensor, GoPro camera, Iphone pic Spectral Data: SVC HR-1024i field spectroradiometer (350-2500 nm) Soil grab Samples for Soil Organic Carbon analysis and Soil bulk density samples In summary, for Initial testing, data from low-cost sensors was used to predict bulk density measured from the grab soil samples from the field. A random forest model was trained based on data from set 1 and set 2 of low-cost sensors, and Hanna sensor. Set 1 and Set 2 were the exact same replica of the same set of low-cost sensors. Two replicas were used to check sensor-to-sensor fluctuations. Preliminary results indicated that the three most important soil properties to predict soil bulk density were soil temperature, soil pH, and soil redox potential. Both sets of low-cost sensors (Set 1 and Set 2) performed considerably better than Hanna sensor. However, there was a significant difference between the performance of Set 1 and Set 2 sensors, which indicates sensor-to-sensor fluctuations. To get more confidence in low-cost sensor performance, more field data was collected, which is being analyzed in the lab. Use of Low-cost sensors seems plausible, and it is anticipated that the analysis of all the data collected will give us more confidence about their performance. Once proven that low-cost sensors can be used to predict complex soil properties such as bulk density and soil organic carbon, we plan t deploy the sensor on our cyber-enabled AweSOMSense platform for automated data collection. This would make soil organic carbon monitoring cost-effective and time effcient. After finalizing the configuration of the platform, they will be deployed at two sites over the Summer 2023 for longer-term testing and data collection. Five new soil cores representing the third broad study area in Georgia were collected in June 2022 from South Newport River in Townsend, Georgia.Soil cores collected from Sapelo Island in 2021 were transported to UNC-Wilmington (UNCW) to complete analyses. Samples were dried, sieved, and combusted for loss-on-ignition determination. In addition, samples have all been pulverized and analyzed for total C content, with fewer than 5% of samples to complete for C content in the coming month(s). Samples collected at South Newport River were transported to UGA Athens campus where they were split, sectioned into 5 cm increments, sensed, and processed for transport to UNCW. At UNCW, soil samples were dried, sieved, and analyzed for moisture content. A subsample was then analyzed by loss-on-ignition method. The remaining sample was pulverized and run for total carbon content on an elemental analyzer. Fifteen of the 90 samples from South Newport have been analyzed for total C content, and more are in process. In addition to the methods of laboratory analyses proposed, stable isotope analysis and laser particle size analysis is being explored. To date, approximately 70% of samples collected from Sapelo Island have been analyzed for stable C and N isotopes at UNC Wilmington. Quality control efforts will reduce that number substantially.
Publications
- Type:
Journal Articles
Status:
Published
Year Published:
2022
Citation:
Sharma, R., Mishra, D. R., Levi, M. R., & Sutter, L. A. (2022). Remote Sensing of Surface and Subsurface Soil Organic Carbon in Tidal Wetlands: A Review and Ideas for Future Research. Remote Sensing, 14(12), 121. https://doi.org/10.3390/rs14122940
- Type:
Journal Articles
Status:
Published
Year Published:
2022
Citation:
Jianwei Hao, Piyush Subedi, In Kee Kim, Lakshmish Ramaswamy, Reaching for the Sky: Maximizing Deep Learning Inference Throughput on Edge Devices with AI Multi-tenancy, ACM Transactions on Internet Technology (ACM TOIT), 2022
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2022
Citation:
Sharma, R., Hao, J., Kim, S., Ramaswamy, L., Mishra, D. R., Kim, I.K., Sutter, L. A. SitS AweSOMSense: Multi-modal Sensing and Analytics Framework for Modelling Belowground SOM in Salt Marsh Wetlands; Second Principal Investigators Workshop for Signals in the Soil (SitS) May 2022, Harpenden, UK
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2022
Citation:
Sharma, R., Mishra, D. R., A Smart-Sensing Cyberinfrastructure for Monitoring Belowground Soil Organic Carbon in Tidal Wetlands; American Association of Geographers (AAG), Feb 2022, PowerPoint presentation, Virtual
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2022
Citation:
Sharma, R., Hao, J., Mishra, D. R., Kim, I.K., Kim, S., Ramaswamy, L., Sutter, L. A. Cyberinfrastructure to Monitor Soil Organic Matter in Salt Marshes of the Georgia Coast; NSF 2022 All Scientists Meeting LTER (long term ecological research), Aug 2022, Pacific Grove, CA
- Type:
Conference Papers and Presentations
Status:
Published
Year Published:
2023
Citation:
Sharma, R., Hao, J., Fleming, M. B., Mishra, D. R., Kim, I.K., Kim, S., Ramaswamy, L., Sutter, L. A. Low-Cost Sensors to Monitor Soil Organic Matter in Salt Marshes; GCE (Georgia Coastal Ecosystem) LTER Annual Meeting; Jan 2023, Athens, GA
|
Progress 02/15/21 to 02/14/22
Outputs
Target Audience:Our team has foster relationships with the team of the NSF's GA Coastal Ecosystem Long Term Ecological Research (GCE-LTER) project and coordinated our efforts with GCE-LTER's ongoing long-term data collection programs to augment and expand our field data. We also participated in the Georgia Coastal Research Council meeting to network with other in-state researchers.We also have contacted with Georgia Department of Transportation (Natural Resources Division)that is interested in coastal restorationto strategize the dissemination of project information. Changes/Problems:The field data collection continuedto suffer in the wake of the COVID-19 pandemic. Althoughthe research team has remained prepared for field works, some delays and no cost extension (NCE) for USDA-NIFA's approval is acticipated.The research team will submit a NCE request after the first anniversary date. What opportunities for training and professional development has the project provided?
Nothing Reported
How have the results been disseminated to communities of interest?
Nothing Reported
What do you plan to do during the next reporting period to accomplish the goals?Platform The research team will createa sensing platform to hold and protect the sensors and devices on a fixed spot in wetlands. More specifically, the arms and legs are built with 2" PVC, and the central post is 4''. And, the solar panel is exposed outside. The camera, power management chip (Witty Pi), and Raspberry Pi are installed inside the post. The post is waterproof by sealing the bottom and capping the top.The wildlife camera, action camera, iPhone 7 will be attached to the platformto collect the field marsh soil images. Nix mini and Nix pro will also be attached to the platform toscan the soil color by direct touch on the soil. Raspberry Pi will be used as the edge server to collect the sensing data and take the computation work. Solar panel will be used to generate power that is supplied to Raspberry Pi and sensors.
Impacts
What was accomplished under these goals?
Wetlands store almost 20%-25% of the world's soil organic carbon (SOC) stock in the form of soil organic matter (SOM) with just 4%-6% of the world's land area (Yu et al., 2012). However, recent studies have indicated striking losses of wetlands in places like North America, where wetland loss is estimated to be 53% in the contiguous United States, 16% in Canada, and 62% in Mexico (Cavallaro et al., 2018; Kolka et al., 2018). Wetlands are the most extensive reservoir of soil organic carbon (SOC), and the loss of this carbon often leads to major increases in carbon dioxide in the atmosphere. Therefore, monitoring, modeling, and mapping SOC changes in wetlands become a critical research area. Studies on SOC mapping using remote sensing data and digital soil mapping (DSM) techniques are rare as field-sample-based monitoring of carbon in wetlands can be cost-prohibitive and labor-intensive. To help alleviate this problem, we present a novel cyber-architecture-based data-centric framework referred to as AweSOMSense (A Wetland Soil Organic Matter Sensor). AweSOMSense explores the usability of low bandwidth, continuous, and automated sensing techniques for salt marsh SOC using low-cost and wireless in-situ sensors. AweSOMSense is based on developing remotely operated sensor platforms capable of acquiring data from salt marsh wetlands using Nix color sensors, other soil property sensors for pH, salinity, moisture, Redox potential, temperature, and digital images. All these factors have been linked to SOC in the literature, and there are cheap wireless sensors available that can collect these datasets, log them through Raspberry Pi or Arduino-based computing boards, and transmit them through the cloud to the lab for modeling. Data collected by the sensing platform is sent to an edge layer for sensing stream procurement, sensor deployment management, and sensor fault detection (QA/QC) before the data are uploaded to the cloud. The edge layer sends the refined sensing data to the cloud layer, which stores and analyzes the field sensors and satellite data together in a machine learning framework. The SOC prediction model is validated with field soil core data analyzed for SOC in the lab. We anticipate that a cyberinfrastructure-based data collection approach would help us understand soil processes in lesser-known and data-scarce ecosystems such as salt marsh wetlands. Field sampling and data collection To date, cores have been collected at two locations on three occasions: Skidaway (August 2020, 16 cores), Sapelo (Sept 2021, 15 cores). At each core location and in between them, the soil surface was sensed using SuperGER hyperspectral, Nix color sensor, and other field soil properties (pH, salinity, and redox) via handheld instrument. During the September samples at Dean Creek, sample collection was synchronized with drone data collection that had hyperspectral, multispectral, and Lidar sensors. Laboratory sample processing and data collection Deep cores from both Skidaway and Sapelo were transported from Sapelo Island to the UGA Athens campus. These soil cores were sliced, and hyperspectral and Nix color readings were made on the fresh cuts at 5 cm depth intervals. The sectioned soil samples were then divided in 5 cm intervals. Slices were subsampled for bulk measurements, and the rest of the sample was used for soil organic carbon measurement. Approximately 100 samples have been pulverized; the remaining samples are in progress. Bulk density and soil moisture has been collected from all samples, and some loss on ignition is complete. After pulverizing, these samples will be evaluated for carbon content using the dry combustion method to calibrate the loss-on-ignition method. Soil organic carbon analysis is in progress. Bulk density and soil moisture-based inferences are discussed in later sections. Results The hyperspectral sensor used in the lab for soil depth at 5 cm interval provides a 1 nm bandwidth from the range of 350 nm to 2500 nm. Water bands around 1450 nm and 1950 nm were very apparent, but a subtle dip around 1200 nm. However, around 970 nm there is a break in spectra for the Flux tower site. This could be due to sensor fluctuations and needs to be checked for other locations. Prominent water absorption signals confirm the saturated condition of soils in wetlands. Other than the water absorption band there is also a chlorophyll absorption feature around 650-700 nm, this is because of organic matter, diatoms, and other plant biomass in soils. There is also a weak kaolinite absorption around 2200 nm, however, kaolinite is more prominent in northern Georgia than in Coastal Georgia (Demattê et al., 2017; Woodruff et al., 2015). The influence of organic matter makes the spectra concave and decreases the reflectance in general, in the visible light region of the spectra (Demattê et al., 2017). There is a weak concave shape and less reflectance for lower depth that may reflect for higher organic matter, comparison of spectral signals with soil organic matter measurement would help to understand it more. Soil organic carbon and soil bulk density are related soil properties. As soil organic carbon measurements were still in progress, soil bulk density readings were used for further analysis. The objective was to predict soil bulk density for various soil depths using hyperspectral bands. A correlation plot was made between spectral bands and bulk density measurements from various depths. The Pearson correlation coefficient between spectral bands and bulk density measurements ranges from 25% to 50%. Then spectral bands with higher correlation from the neighboring bands, apparent from a small hump were chosen to be used as covariables for a model. A total of 6 bands were chosen and they were 565-575 nm, 665-675 nm, 1470-1480 nm, 1875-1885 nm, 2205-2215 nm, and 2310-2320 nm. The correlation coefficient between bulk density and six selected bands ranges from 31 to 50%. However, there is high collinearity between some of the bands like Band 565-575 nm and 665-675 nm. All the bands have a higher than 60% correlation with each other that could bring multicollinearity in the models and needs to be accounted for.The linear model between bulk density and six selected bands explained around 31% of the variability. Out of six bands, band 1875-1885 nm, band 2205-2215 nm, and band 2310-2320 nm were significant for the model at a 5% significance level. A random forest-based model did slightly better. The variability explained by the model for training data was 91% (R2) but explained variability drops drastically for testing data to 24%. The drop in R2 for testing data could be because of collinearity or overfitting.
Publications
- Type:
Journal Articles
Status:
Published
Year Published:
2021
Citation:
Salehi Hikouei, I.; Kim, S.S.; Mishra, D.R. Machine-Learning Classification of Soil Bulk Density in Salt Marsh Environments. Sensors 2021, 21, 4408. https://doi.org/
10.3390/s21134408
|