An official website of the United States government
Soil organic carbon (SOC) represents the largest terrestrial carbon pool. Effectively monitoring SOC at high spatial resolution is crucial for estimating carbon budgets at the ecosystem scale and informing climate change mitigation efforts at the regional scale. Traditional soil sampling methods, however, are laborious and expensive. Remote sensing platforms can be used to survey large landscapes to meet the need for rapid and cost-effective approaches for quantifying SOC at landscape to regional scales, if relationships between remotely sensed variables and SOC can be established. We developed a workflow to analyze and predict SOC content based on National Ecological Observatory Network (NEON) Airborne Observation Platform (AOP) remote sensing data. First, we benchmarked related tools and developed reproducible workflows using NEON remote sensing datasets. Hyperspectral data were extracted from the locations where NEON soil data exist. Additional variables from the LiDAR data and key metadata (climate and land cover) were extracted for those locations. Random Forest and Partial Least Squares Regression techniques were then used to create models for fine-scale SOC prediction. Cross-validation was embedded in the model creation step. The most important covariates were selected through recursive feature elimination, stepwise selection, and expert judgment. Preliminary results indicate that machine learning models can re-produce SOC measurements in testing datasets. Key predictors include topographic variables, vegetation indices, and specific wavelength bands in hyperspectral images. We are further validating our algorithms using SOC data from ISCN (International Soil Carbon Network) and SoDaH (SOils DAta Harmonization database) that are co-located with NEON sites. We are creating high-resolution SOC maps for 0-30 cm depth at NEON sites and testing our algorithms for different land use types. Our work paves the way for a broader assessment of SOC stocks using remote sensing observations, and our high-resolution SOC maps will potentially help quantify carbon budgets across heterogeneous landscapes.
more »
« less
Handheld lidar sensors can accurately measure aboveground biomass
Many recent studies have explored remote sensing approaches to facilitate non‐destructive sampling of aboveground biomass (AGB). Lidar platforms (e.g., iPhone and iPad PRO models) have recently made remote sensing technologies widely available and present an alternative to traditional approaches for estimating AGB. Lidar approaches can be completed within a fraction of the time required by many analog methods. However, it is unknown if handheld sensors are capable of accurately predicting AGB or how different modeling techniques affect prediction accuracy. Here, we collected AGB from 0.25‐m2plots (N = 45) from three sites along an elevational gradient within rangelands surrounding Flagstaff, Arizona, USA. Each plot was scanned with a mobile laser scanner (MLS) and iPad before plants were clipped, dried, and weighed. We compared the capability of iPad and MLS sensors to estimate AGB via minimization of model normalized root mean square error (NRMSE). This process was performed on predictor subsets describing structural, spectral, and field‐based characteristics across a suite of modeling approaches including simple linear, stepwise, lasso, and random forest regression. We found that models developed from MLS and iPad data were equally capable of predicting AGB (NRMSE 26.6% and 29.3%, respectively) regardless of the variable subsets considered. We also found that stepwise regression regularly resulted in the lowest NRMSE. Structural variables were consistently selected during each modeling approach, while spectral variables were rarely included. Field‐based variables were important in linear regression models but were not included after variable selection within random forest models. These findings support the notion that remote sensing techniques offer a valid alternative to analog field‐based data collection methods. Together, our results demonstrate that data collected using a more widely available platform will perform similarly to a more costly option and outline a workflow for modeling AGB using remote sensing systems alone.
more »
« less
- Award ID(s):
- 1906243
- PAR ID:
- 10630751
- Publisher / Repository:
- Wiley
- Date Published:
- Journal Name:
- Ecosphere
- Volume:
- 16
- Issue:
- 6
- ISSN:
- 2150-8925
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Grassy ecosystems cover >25% of the world's land surface area. The abundance of herbaceous vegetation in these systems directly impacts a variety of ecological processes, including carbon sequestration, regulation of water and nutrient cycling, and support of grazing wildlife and livestock. Efforts to quantify herbaceous biomass, however, are often limited by a trade‐off between accuracy and spatial scale. Here, we describe a method for using Light Detection and Ranging (LiDAR) to estimate continuous aboveground biomass (AGB) at sub‐meter resolutions over large (10–10 000 ha) spatial scales. Across two African savanna ecosystems, we compared field‐ and LiDAR‐derived structural metrics—including measures of vegetation height and volume—with destructively harvested AGB by aligning our geospatial data with the location of harvested quadrats. Using this combination of approaches, we develop scaling equations to estimate spatially continuous herbaceous AGB over large areas. We demonstrate the utility of this method using a long‐term, large herbivore exclosure experiment as a case study and comprehensively compare common field‐ and LiDAR‐derived metrics for estimating herbaceous AGB. Our results indicate that UAV‐borne LiDAR provides comparable accuracy to standard field methods but over considerably larger areas. Nearly every measure of vegetation structure we quantified using LiDAR provided estimates of AGB that were comparable in accuracy (R2 > 0.6) to the suite of common field methods we evaluated. However, marked differences between our two sites indicate that, for applications where accurate estimation of absolute biomass is a priority, site‐specific parameterization with destructive harvesting is necessary regardless of methodology. With the increasing availability of high‐resolution remote sensing data globally, our results indicate that many measures of herbaceous vegetation structure can be used to accurately compare AGB, even in the absence of complementary field data.more » « less
-
Abstract Climate change is driving substantial changes in North American boreal forests, including changes in productivity, mortality, recruitment, and biomass. Despite the importance for carbon budgets and informing management decisions, there is a lack of near‐term (5–30 year) forecasts of expected changes in aboveground biomass (AGB). In this study, we forecast AGB changes across the North American boreal forest using machine learning, repeat measurements from 25,000 forest inventory sites, and gridded geospatial datasets. We find that AGB change can be predicted up to 30 years into the future, and that training on sites across the entire domain allows accurate predictions even in regions with only a small amount of existing field data. While predicting AGB loss is less skillful than gains, using a multi‐model ensemble can improve the accuracy in detecting change direction to >90% for observed increases, and up to 70% for observed losses. Higher stem density, winter temperatures, and the presence of temperate tree species in forest plots were positively associated with AGB change, whereas greater initial biomass, continentality (difference between mean summer and winter temperatures), prevalence of black spruce (Picea mariana), summer precipitation, and early warning metrics from long‐term remote sensing time series were negatively associated with AGB change. Across the domain, we predict nondisturbance‐induced declines in AGB at 23% of sites by 2030. The approach developed here can be used to estimate near‐future forest biomass in boreal North America and inform relevant management decisions. Our study also highlights the power of machine learning multi‐model ensembles when trained on a large volume of forest inventory plots, which could be applied to other regions with adequate plot density and spatial coverage.more » « less
-
null (Ed.)Timely updates of carbon stock distribution are needed to better understand the impacts of deforestation and degradation on forest carbon stock dynamics. This research aimed to explore an approach for estimating aboveground carbon density (ACD) in the Brazilian Amazon through integration of MODIS (moderate resolution imaging spectroradiometer) and a limited number of light detection and ranging (Lidar) data samples using linear regression (LR) and random forest (RF) algorithms, respectively. Airborne LiDAR data at 23 sites across the Brazilian Amazon were collected and used to calculate ACD. The ACD estimation model, which was developed by Longo et al. in the same study area, was used to map ACD distribution in the 23 sites. The LR and RF methods were used to develop ACD models, in which the samples extracted from LiDAR-estimated ACD were used as dependent variables and MODIS-derived variables were used as independent variables. The evaluation of modeling results indicated that ACD can be successfully estimated with a coefficient of determination of 0.67 and root mean square error of 4.18 kg C/m2 using RF based on spectral indices. The mixed pixel problem in MODIS data is a major factor in ACD overestimation, while cloud contamination and data saturation are major factors in ACD underestimation. These uncertainties in ACD estimation using MODIS data make it difficult to examine annual ACD dynamics of degradation and growth, however this method can be used to examine the deforestation-induced ACD loss.more » « less
-
Abstract Understanding the severity and extent of near surface critical zone (CZ) disturbances and their ecosystem response is a pressing concern in the face of increasing human and natural disturbances. Predicting disturbance severity and recovery in a changing climate requires comprehensive understanding of ecosystem feedbacks among vegetation and the surrounding environment, including climate, hydrology, geomorphology, and biogeochemistry. Field surveys and satellite remote sensing have limited ability to effectively capture the spatial and temporal variability of disturbance and CZ properties. Technological advances in remote sensing using new sensors and new platforms have improved observations of changes in vegetation canopy structure and productivity; however, integrating measures of forest disturbance from various sensing platforms is complex. By connecting the potential for remote sensing technologies to observe different CZ disturbance vectors, we show that lower severity disturbance and slower vegetation recovery are more difficult to quantify. Case studies in montane forests from the western United States highlight new opportunities, including evaluating post‐disturbance forest recovery at multiple scales, shedding light on understory vegetation regrowth, detecting specific physiological responses, and refining ecohydrological modeling. Learning from regional CZ disturbance case studies, we propose future directions to synthesize fragmented findings with (a) new data analysis using new or existing sensors, (b) data fusion across multiple sensors and platforms, (c) increasing the value of ground‐based observations, (d) disturbance modeling, and (e) synthesis to improve understanding of disturbance.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Journal Article:
- https://doi.org/10.1002/ecs2.70232
