Accurate predictions of crop yield are critical for developing effective agricultural and food policies at the regional and global scales. We evaluated a machine-learning method, Random Forests (RF), for its ability to predict crop yield responses to climate and biophysical variables at global and regional scales in wheat, maize, and potato in comparison with multiple linear regressions (MLR) serving as a benchmark. We used crop yield data from various sources and regions for model training and testing: 1) gridded global wheat grain yield, 2) maize grain yield from US counties over thirty years, and 3) potato tuber and maize silage yield from the northeastern seaboard region. RF was found highly capable of predicting crop yields and outperformed MLR benchmarks in all performance statistics that were compared. For example, the root mean square errors (RMSE) ranged between 6 and 14% of the average observed yield with RF models in all test cases whereas these values ranged from 14% to 49% for MLR models. Our results show that RF is an effective and versatile machine-learning method for crop yield predictions at regional and global scales for its high accuracy and precision, ease of use, and utility in data analysis. RF may result in a loss of accuracy when predicting the extreme ends or responses beyond the boundaries of the training data.
Lidar remote sensing has been used to survey stream channel and floodplain topography for decades. However, traditional platforms, such as aerial laser scanning (ALS) from an airplane, have limitations including flight altitude and scan angle that prevent the scanner from collecting a complete survey of the riverscape. Drone laser scanning (DLS) or unmanned aerial vehicle (UAV)-based lidar offer ways to scan riverscapes with many potential advantages over ALS. We compared point clouds and lidar data products generated with both DLS and ALS for a small gravel-bed stream, Stroubles Creek, located in Blacksburg, VA. Lidar data points were classified as ground and vegetation, and then rasterized to produce digital terrain models (DTMs) representing the topography and canopy height models (CHMs) representing the vegetation. The results highlighted that the lower-altitude, higher-resolution DLS data were more capable than ALS of providing details of the channel profile as well as detecting small vegetation on the floodplain. The greater detail gained with DLS will provide fluvial researchers with better estimates of the physical properties of riverscape topography and vegetation.
Data concerning streambank retreat ͑SBR͒ rates are important for many different engineering applications such as stream restoration and total maximum daily load ͑TMDL͒ development. However, measurement of SBR can be time-consuming and is often characterized by large measurement and interpolation errors. These errors propagate into the calculation of sediment budgets for the development of TMDLs, creating uncertainty in source partitioning and overall load estimates. We compared two techniques for measuring SBR: ͑1͒ traditional surveying with a total station and ͑2͒ terrestrial laser scanning ͑TLS͒. An 11-m streambank on Stroubles Creek in Blacksburg, Virgina was surveyed six times over a 2-year period. The average SBR along the entire bank was estimated to be Ϫ0.15 m/year with TLS and Ϫ0.18 m/year with total station surveying. The resulting differences in median SBR estimates along five distinct cross sections between each of the survey dates ranged from Ϫ0.11 to +0.06 m. This error in SBR due to total station surveying would be significant when extrapolating to a reach-or watershed-scale estimate of sediment load due to SBR. In addition, TLS collects data across the entire streambank surface, rather than just at distinct cross sections, providing much more information concerning SBR volumes and spatial variability.
The delivery of herbaceous feedstock from satellite storage locations (SSLs) to a biorefinery or preprocessing depot is a logistics problem that must be optimized before a new bioenergy industry can be realized. Both load-out productivity, defined as the loading of 5 × 4 round bales into a 20-bale rack at the SSL, and truck productivity, defined as the hauling of bales from the SSLs to the biorefinery, must be maximized. Productivity (Mg/d) is maximized and cost (USD/Mg) is minimized when approximately the same number the loads is received each day. To achieve this, a central control model is proposed, where a feedstock manager at the biorefinery can dispatch a truck to any SSL where a load will be available when the truck arrives. Simulations of this central control model for different numbers of simultaneous load-out operations were performed using a database of potential production fields within a 50 km radius of a theoretical biorefinery in Gretna, VA. The minimum delivered cost (i.e., load-out plus truck) was achieved with nine load-outs and a fleet of eight trucks. The estimated cost was 11.24 and 11.62 USD/Mg of annual biorefinery capacity (assuming 24/7 operation over 48 wk/y for a total of approximately 150,000 Mg/y) for the load-out and truck, respectively. The two costs were approximately equal, reinforcing the desirability of a central control to maximize the productivity of these two key operations simultaneously.
Accurate stream topography measurement is important for many ecological applications such as hydraulic modeling and habitat characterization. Habitat complexity measures are often made using visual approximations or total station (TS) surveying that can be subjective and have limited spatial resolution. Terrestrial laser scanning (TLS) can measure topography at a high resolution and accuracy. Two methods, TS surveying and TLS, were compared for measuring complex topography in a boulder-dominated 100 m forested reach of the Staunton River in Shenandoah National Park, Virginia. The mean absolute difference between the two datasets was 0.11 m with 82.3 percent of the TS data within Ϯ0.1 m of TLS. The TLS dataset was processed to remove vegetation and create a 2 cm digital elevation model (DEM). An algorithm was developed for delineating rocks within the stream channel from the DEM. A common ecological metric based on the structural complexity of the stream, percent in-stream rock cover, was calculated from the TLS dataset, and the results were compared to estimates from traditional methods. This application illustrates the potential of TLS to quantify habitat complexity measures in an automated, unbiased manner.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.