Daniel M. Howard

Crop classification modelling using remote sensing and environmental data in the Greater Platte River Basin, USA

With an ever expanding population, potential climate variability and an increasing demand for agriculture-based alternative fuels, accurate agricultural land-cover classification for specific crops and their spatial distributions are becoming critical to researchers, policymakers, land managers and farmers. It is important to ensure the sustainability of these and other land uses and to quantify the net impacts that certain management practices have on the environment. Although other quality crop classification products are often available, temporal and spatial coverage gaps can create complications for certain regional or time-specific applications. Our goal was to develop a model capable of classifying major crops in the Greater Platte River Basin (GPRB) for the post-2000 era to supplement existing crop classification products. This study identifies annual spatial distributions and area totals of corn, soybeans, wheat and other crops across the GPRB from 2000 to 2009. We developed a regression tree classification model based on 2.5 million training data points derived from the National Agricultural Statistics Service (NASS) Cropland Data Layer (CDL) in relation to a variety of other relevant input environmental variables. The primary input variables included the weekly 250 m US Geological Survey Earth Observing System Moderate Resolution Imaging Spectroradiometer normalized differential vegetation index, average long-term growing season temperature, average long-term growing season precipitation and yearly start of growing season. An overall model accuracy rating of 78% was achieved for a test sample of roughly 215 000 independent points that were withheld from model training. Ten 250 m resolution annual crop classification maps were produced and evaluated for the GPRB region, one for each year from 2000 to 2009. In addition to the model accuracy assessment, our validation focused on spatial distribution and county-level crop area totals in comparison with the NASS CDL and county statistics from the US Department of Agriculture (USDA) Census of Agriculture. The results showed that our model produced crop classification maps that closely resembled the spatial distribution trends observed in the NASS CDL and exhibited a close linear agreement with county-by-county crop area totals from USDA census data (R 2 = 0.90).

Application-Ready Expedited MODIS Data for Operational Land Surface Monitoring of Vegetation Condition

Monitoring systems benefit from high temporal frequency image data collected from the Moderate Resolution Imaging Spectroradiometer (MODIS) system. Because of near-daily global coverage, MODIS data are beneficial to applications that require timely information about vegetation condition related to drought, flooding, or fire danger. Rapid satellite data streams in operational applications have clear benefits for monitoring vegetation, especially when information can be delivered as fast as changing surface conditions. An “expedited” processing system called “eMODIS” operated by the U.S. Geological Survey provides rapid MODIS surface reflectance data to operational applications in less than 24 h offering tailored, consistently-processed information products that complement standard MODIS products. We assessed eMODIS quality and consistency by comparing to standard MODIS data. Only land data with known high quality were analyzed in a central U.S. study area. When compared to standard MODIS (MOD/MYD09Q1), the eMODIS Normalized Difference Vegetation Index (NDVI) maintained a strong, significant relationship to standard MODIS NDVI, whether from morning (Terra) or afternoon (Aqua) orbits. The Aqua eMODIS data were more prone to noise than the Terra data, likely due to differences in the internal cloud mask used in MOD/MYD09Q1 or compositing rules. Post-processing temporal smoothing decreased noise in eMODIS data.

Correction to “Upscaling carbon fluxes over the Great Plains grasslands: Sinks and sources”

] The paper “Upscaling carbon fluxes over the GreatPlains grasslands: Sinks and sources” by L. Zhang et al.(JournalofGeophysicalResearch,116,G00J03,doi:10.1029/2010JG001504, 2011) contains an error. In paragraphs 1,20, and 32, the statement “the regional averaged NEP forthe entire Great Plains grasslands was estimated to be336 Tg C yr

Mapping carbon flux uncertainty and selecting optimal locations for future flux towers in the Great Plains

Flux tower networks (e.g., AmeriFlux, Agriflux) provide continuous observations of ecosystem exchanges of carbon (e.g., net ecosystem exchange), water vapor (e.g., evapotranspiration), and energy between terrestrial ecosystems and the atmosphere. The long-term time series of flux tower data are essential for studying and understanding terrestrial carbon cycles, ecosystem services, and climate changes. Currently, there are 13 flux towers located within the Great Plains (GP). The towers are sparsely distributed and do not adequately represent the varieties of vegetation cover types, climate conditions, and geophysical and biophysical conditions in the GP. This study assessed how well the available flux towers represent the environmental conditions or “ecological envelopes” across the GP and identified optimal locations for future flux towers in the GP. Regression-based remote sensing and weather-driven net ecosystem production (NEP) models derived from different extrapolation ranges (10 and 50%) were used to identify areas where ecological conditions were poorly represented by the flux tower sites and years previously used for mapping grassland fluxes. The optimal lands suitable for future flux towers within the GP were mapped. Results from this study provide information to optimize the usefulness of future flux towers in the GP and serve as a proxy for the uncertainty of the NEP map.

An Optimal Sample Data Usage Strategy to Minimize Overfitting and Underfitting Effects in Regression Tree Models Based on Remotely-Sensed Data

Regression tree models have been widely used for remote sensing-based ecosystem mapping. Improper use of the sample data (model training and testing data) may cause overfitting and underfitting effects in the model. The goal of this study is to develop an optimal sampling data usage strategy for any dataset and identify an appropriate number of rules in the regression tree model that will improve its accuracy and robustness. Landsat 8 data and Moderate-Resolution Imaging Spectroradiometer-scaled Normalized Difference Vegetation Index (NDVI) were used to develop regression tree models. A Python procedure was designed to generate random replications of model parameter options across a range of model development data sizes and rule number constraints. The mean absolute difference (MAD) between the predicted and actual NDVI (scaled NDVI, value from 0–200) and its variability across the different randomized replications were calculated to assess the accuracy and stability of the models. In our case study, a six-rule regression tree model developed from 80% of the sample data had the lowest MAD (MADtraining = 2.5 and MADtesting = 2.4), which was suggested as the optimal model. This study demonstrates how the training data and rule number selections impact model accuracy and provides important guidance for future remote-sensing-based ecosystem modeling.

Grassland and Cropland Net Ecosystem Production of the U.S. Great Plains: Regression Tree Model Development and Comparative Analysis

This paper presents the methodology and results of two ecological-based net ecosystem production (NEP) regression tree models capable of up scaling measurements made at various flux tower sites throughout the U.S. Great Plains. Separate grassland and cropland NEP regression tree models were trained using various remote sensing data and other biogeophysical data, along with 15 flux towers contributing to the grassland model and 15 flux towers for the cropland model. The models yielded weekly mean daily grassland and cropland NEP maps of the U.S. Great Plains at 250 m resolution for 2000–2008. The grassland and cropland NEP maps were spatially summarized and statistically compared. The results of this study indicate that grassland and cropland ecosystems generally performed as weak net carbon (C) sinks, absorbing more C from the atmosphere than they released from 2000 to 2008. Grasslands demonstrated higher carbon sink potential (139 g C·m−2·year−1) than non-irrigated croplands. A closer look into the weekly time series reveals the C fluctuation through time and space for each land cover type.

The Solar and Southern Oscillation Components in the Satellite Altimetry Data

With satellite altimetry data accumulating over the past two decades, the mean sea level (MSL) can now be measured to unprecedented accuracy. We search for physical processes which can explain the sea level variations and find that at least 70% of the variance in the annually smoothed detrended altimetry data can be explained as the combined effect of both the solar forcing and the El Nino–Southern Oscillation (ENSO). The phase of the solar component can be used to derive the different steric and eustatic contributions. We find that the peak to peak radiative forcing associated with the solar cycle is 1.33 ± 0.34 W/m2, contributing a 4.4 ± 0.8 mm variation. The slow eustatic component (describing, for example, the cryosphere and large bodies of surface water) has a somewhat smaller peak to peak amplitude of 2.4 ± 0.6 mm. Its phase implies that warming the oceans increases the ocean water loss rate. Additional much smaller terms include a steric feedback term and a fast eustatic term. The ENSO contributes a peak to peak variation of 5.5 ± 0.8 mm, predominantly through a direct effect on the MSL and significantly less so indirectly through variations in the radiative forcing.

Temporal expansion of annual crop classification layers for the CONUS using the C5 decision tree classifier

ABSTRACT Crop cover maps have become widely used in a range of research applications. Multiple crop cover maps have been developed to suite particular research interests. The National Agricultural Statistics Service (NASS) Cropland Data Layers (CDL) are a series of commonly used crop cover maps for the conterminous United States (CONUS) that span from 2008 to 2013. In this investigation, we sought to contribute to the availability of consistent CONUS crop cover maps by extending temporal coverage of the NASS CDL archive back eight additional years to 2000 by creating annual NASS CDL-like crop cover maps derived from a classification tree model algorithm. We used over 11 million records to train a classification tree algorithm and develop a crop classification model (CCM). The model was used to create crop cover maps for the CONUS for years 2000–2013 at 250 m spatial resolution. The CCM and the maps for years 2008–2013 were assessed for accuracy relative to resampled NASS CDLs. The CCM performed well against a withheld test data set with a model prediction accuracy of over 90%. The assessment of the crop cover maps indicated that the model performed well spatially, placing crop cover pixels within their known domains; however, the model did show a bias towards the ‘Other’ crop cover class, which caused frequent misclassifications of pixels around the periphery of large crop cover patch clusters and of pixels that form small, sparsely dispersed crop cover patches.

Rapid Crop Cover Mapping for the Conterminous United States

Timely crop cover maps with sufficient resolution are important components to various environmental planning and research applications. Through the modification and use of a previously developed crop classification model (CCM), which was originally developed to generate historical annual crop cover maps, we hypothesized that such crop cover maps could be generated rapidly during the growing season. Through a process of incrementally removing weekly and monthly independent variables from the CCM and implementing a ‘two model mapping’ approach, we found it viable to generate conterminous United States-wide rapid crop cover maps at a resolution of 250 m for the current year by the month of September. In this approach, we divided the CCM model into one ‘crop type model’ to handle the classification of nine specific crops and a second, binary model to classify the presence or absence of ‘other’ crops. Under the two model mapping approach, the training errors were 0.8% and 1.5% for the crop type and binary model, respectively, while test errors were 5.5% and 6.4%, respectively. With spatial mapping accuracies for annual maps reaching upwards of 70%, this approach demonstrated a strong potential for generating rapid crop cover maps by the 1st of September.

Estimating carbon and showing impacts of drought using satellite data in regression-tree models

ABSTRACT Integrating spatially explicit biogeophysical and remotely sensed data into regression-tree models enables the spatial extrapolation of training data over large geographic spaces, allowing a better understanding of broad-scale ecosystem processes. The current study presents annual gross primary production (GPP) and annual ecosystem respiration (RE) for 2000–2013 in several short-statured vegetation types using carbon flux data from towers that are located strategically across the conterminous United States (CONUS). We calculate carbon fluxes (annual net ecosystem production [NEP]) for each year in our study period, which includes 2012 when drought and higher-than-normal temperatures influence vegetation productivity in large parts of the study area. We present and analyse carbon flux dynamics in the CONUS to better understand how drought affects GPP, RE, and NEP. Model accuracy metrics show strong correlation coefficients (r) (r ≥ 94%) between training and estimated data for both GPP and RE. Overall, average annual GPP, RE, and NEP are relatively constant throughout the study period except during 2012 when almost 60% less carbon is sequestered than normal. These results allow us to conclude that this modelling method effectively estimates carbon dynamics through time and allows the exploration of impacts of meteorological anomalies and vegetation types on carbon dynamics.