Online tools such as the Truterra Insights Engine (IE) provide key performance indicator (KPI) assessments supporting farmer decisions to sustainably produce and deliver crops to market (https://www.truterraag.com/). They enable farmers to analyze and improve the long-term health of their ag-operations and participate in resilient supply chains. For example, IE leverages four physically-based models and algorithms for creating data used to assess cropping system KPIs for water and wind soil erosion, soil organic matter trend, and greenhouse gas emissions. Its scope spans 19 states from Minnesota to Louisiana, and from Kansas to Pennsylvania. Currently, IE supports assessments of six crop rotations (corn, soybeans, wheat), four tillage regimes, six cover crop options, six nitrogen fertilization methods, and six conservation practice combinations across the soils and climates of the 19 states. The existing models used to create the KPI dataset require relatively extensive data input and take significant time to finish a simulation, thus they are not suitable for direct real-time use. By contrast, surrogate models (SM) require many fewer inputs and finish quickly, but are constrained by a defined spatial coverage and providing less precise results. The challenge is to achieve a solution balancing rapid, scientifically valid, sufficiently precise, and applicable results for the regions of interest. Recent advances in machine learning combined with a streamlined SM delineation (Serafin, 2019; Serafin et al., 2021) offer potential for significantly improving surrogate model availability, precision, and applicability. For estimating water induced sheet and rill erosion for KPI assessments we employed the WEPP (Water Erosion Prediction Project) model as the process-based technology for prediction of soil erosion by water at hillslope profile, field, and small watershed scales. The overall objective of this ongoing modeling effort is the creation of a surrogate model for WEPP to produce erosion estimates at the field scale within a given region while: 1) creating surrogate erosion estimates within the range of 10-20% relative RMSE of WEPP results, 2) minimizing the number of required surrogate model inputs, and 3) consistently creating SM erosion results within seconds. We focused our study on rotations of Corn-Soybean, Continuous Corn, Corn-Winter Wheat, Corn-Sorghum in the Central Great Plains (LRR H), creating 5M WEPP simulation scenarios, permuting the inputs for yield, slope steepness and length as well as soil properties. All simulations were executed on a 1200 core Kubernetes cluster, hosting the WEPP CSIP service and supporting Conservation Resources CSIP data services for SSURGO soils, climate and DEM data. Using the CSIP Publish/Subscribe approach (David et al., 2013) for high performance model executions, 2.7M result sets were generated and analyzed. Those data sets were used for ML training with LightGBM, a Light Gradient Boosting Machine open-source framework based on decision tree algorithms for ranking and classification. Exploring various approaches for selecting sensitive and representative input data we generated a surrogate model for 16 sensitive SM inputs for precipitation, yield, crop, slope and soil properties to estimate sheet and rill erosion. Results from SM testing are shown in Figure 1. Using ~1.9M training and ~820K test samples (70/30%), selected using a Kolmogorov–Smirnov test, we achieved a RRMSE of 6.4%, KGE of 0.999, and NSE of 0.998 for training and a RRMSE of 8.1%, KGE of 0.998, and NSE of 0.997 for testing. The generated SM was further integrated into an SM KPI service in CSIP, producing erosion estimates for fields within LRR H in 2.8 seconds of SM runtime, adding time to obtain needed inputs. This work is ongoing and the presented results represent a research snapshot. Currently, the authors are exploring supplementing the current method with an ensemble approach to further align the SM output accuracy with the original WEPP output.

Framework Incorporating Complex Uncertain Systems (FICUS) provides geographic risk analysis capabilities that will dramatically improve military intelligence in locations with the Engineer Research and Development’s (ERDC) demographic and infrastructure models built and calibrated. When completed, FICUS would improve intelligence products by incorporating existing tools from the National Geospatial Intelligence Agency, ERDC, and FICUS prototype models, even in places without demographic or infrastructure capabilities. FICUS would support higher-fidelity intelligence analysis of population, environmental, and infrastructure interaction in areas with Human Infrastructure System Assessment (HISA) and urban security models built and calibrated. This technical report will demonstrate FICUS prototype tools that allow Civil Affairs Soldiers to provide situational awareness information via a browser interface.

The Water Erosion Prediction Project (WEPP) model applies processes for water infiltration, soil water percolation, surface runoff, evapotranspiration, raindrop and shear stress soil detachment, sediment transport and deposition, plant growth, residue management and decomposition, and irrigation in simulations to assess the impact of cropping system management on soil and water resources. Extensive use of WEPP on agricultural land usually involves defining a hillslope representing an entire farm field, often for the most erosive soil in the field, good enough for planning purposes. These assessments do not provide a detailed view of soil detachment and flow of water and sediment within the field, thus not providing sufficient information to support precise design, placement, and application of conservation practices. Further, they do not route water and sediment in water courses through a farm or the farms in a small watershed, thus not providing a more detailed view above the field scale. The WEPP spatial application (WEPP-GIS; Figure 1), deployed as a web model service and integrated with Catena-GIS and the Cloud Services Integration Platform (CSIP), provides two options for simulating soil erosion, runoff, and sediment transport: field-flowpath and watershed-flowpath. Field mode simulates all flowpaths within a farm field. A CSIP service employs TauDEM (Tarboton, 2014), utilizes the USGS National Elevation Dataset 10-meter DEM, and clipping to create three delineation input layers: sub-watersheds, stream networks, and all flowpaths in the fields of a farm. Other CSIP services fetch parameters from common domain data sources to create soil and climate input layers. Users define the management of each field using CSIP services to fetch data from a common cropping system domain database to create the management input layer and crop rotation object to be used by the model. The WEPP model simulates each flowpath, iterating through each cell to the edge of the field. With watershed-flowpath mode the user specifies an outlet point on a channel cell, and a CSIP service delineates a traditional watershed above the outlet point, creating a network of sub-watersheds and channels not bounded by farm field boundaries. The CSIP delineation service defines all flowpaths within each sub-watershed, and the model simulates all flowpaths, water and sediment reaching the channel network and routing to the outlet. Large farms and small watersheds can involve a very large number of flowpaths, therefore to the maximum extent possible, simulations are run in parallel to reduce total run-time. Model output is aggregated and rendered to a variety of reports, maps, and graphs informing analysis leading to improved field/farm management alternatives.

Abstract. The Digital Earth (DE) metaphor is very useful for both end users and for hydrological modellers (i.e., the coders). However, in literature it can promote the erroneous view of models as a commodity, that is a basic good used in commerce that is interchangeable with other goods of the same type, without any warning about the fact that some models work better than others, some models just work while others can be simply wrong. These distinctions are at the core of doing good science. This opinion contribution, on the one hand, tries to accept the challenge of adopting models as commodities but, on the other, it wants to show that this acceptance comes with some consequences as to how models must be structured. We analyse different categories of models, with the view of making them part of a Digital eARth Twin Hydrology system (called DARTH). We also stress the idea that DARTHs are not models in and of themselves, rather they need to be built on an appropriate infrastructure that provides some basic services for connection to input data and allows for a modelling-by-components strategy, which, we argue, is the right one for accomplishing the requirements of the DE. The urgency for DARTHs to be Open Source and well written pieces of codes is discussed here in light of the Open Science movement and its ideas. The need to tie predictions to an estimated confidence interval is also supported. Finally, it is argued that DARTHs must promote a new participatory way of doing hydrological science, where researchers can contribute cooperatively to characterize and control model outcomes in various territories. Furthermore, this has consequences for the engineering of the systems.

The Digital Earth (DE) metaphor is very useful for both end users and for hydrological modellers. However, in literature it can promote the erroneous view of models as a commodity, that is a basic good used in commerce that is interchangeable with other goods of the same type, without any warning about the fact that some models work better than others, some models just work while others can be simply wrong. These distinctions are at the core of doing good science. This opinion contribution, on the one hand, tries to accept the challenge of adopting models as commodities but, on the other, it wants to show that this acceptance comes with some consequences as to how models must be structured. The first reuirement is that Digital eARth Twin Hydrology system (called DARTH) need to be Open Source and built with Open Science rules in mind. We analyse different categories of models, with the view of making them part of a . We also stress the idea that DARTHs are not models in and of themselves, rather they need to be built on an appropriate infrastructure that provides some basic services for connection to input data and allows for a modelling-by-components strategy, which, we argue, is the right one for accomplishing the requirements of the DE. The need to tie predictions to an estimated confidence interval is also supported. Finally, it is argued that DARTHs must promote a new participatory way of doing hydrological science, where researchers can contribute cooperatively to characterize and control model outcomes in various territories. Furthermore, this has consequences for the engineering of the systems.

Environmental models are often essential to implement projects in planning, consulting and regulatory institutions. Research models are often poorly suited to such applications due to their complexity, data requirements, operational boundaries, and factors such as institutional capacities. This contribution enhances a modeling framework to help mitigate research model complexity, streamline data and parameter setup, reduce runtime, and improve model infrastructure efficiency. Using a surrogate modeling approach, we capture the intrinsic knowledge of a conceptual or process-based model into an ensemble of artificial neural networks. The enhanced modeling framework interacts with machine learning libraries to derive surrogate models for each model service. This process is secured using blockchain technology. After describing the methods and implementation, we present an example wherein hydrologic peak discharge provided by the curve number model is emulated with a surrogate model ensemble. The ensemble median values outperformed any individual surrogate model fit to the curve number model.

We apply predictive weather metrics and land model sensitivities to improve the Colorado State University Water Irrigation Scheduler for Efficient Application (WISE). WISE is an irrigation decision aid that integrates environmental and user information for optimizing water use. Rainfall forecasts and verification performance metrics are used to estimate predictive rainfall probabilities that are used as input data within the irrigation decision aid. These input data errors are also used within a land model sensitivity study to diagnose important prognostic water movement behaviors for irrigation tool development purposes simultaneously performing the analysis in space and time. Thus, important questions such as “how long can a crop water application be delayed while maintaining crop yield production?” are addressed by evaluating crop growth stage interactions as a function of soil depth (i.e., space), rainfall events (i.e., time), and their probabilistic uncertainties. Editor’s note: This paper is part of the featured series on Optimizing Ogallala Aquifer Water Use to Sustain Food Systems. See the February 2019 issue for the introduction and background to the series.

Application of supervised classification to short-term forecasting of hydrological events demonstrated that combining outputs of several individual learners into a final judgement improves the accuracy of predictions and creates more robust models. Given that predictions are generated as categorical values corresponding to a class label of a future hydrological event, the ensembles perform better when they incorporate black box models which disagree on the same subsets of data. To further extend the ‘diversity of opinions’ of ensemble members, black box models of a different type can be added to an ensemble of classifiers. Given that regression methods are aimed at accurate calculation of future magnitudes of hydrological characteristics as opposed to determining a class label denoting future hydrological conditions, the extension of the ensemble approach to regression and hybrid models looks promising to further increase the lead time of reliable predictions. The study investigated regression models applied for short-term predictions of hydrological events, such as flash floods, at a highly urbanized small watershed and their inclusion into ensembles of classifiers. The predictions were generated solely on readily available data collected by stream and rain gauges. The heterogeneous measurements of water levels and precipitation were combined and transformed into phase spaces using time-delay embedding. The potential for developing a hybrid model incorporating both classification and regression approaches was analysed. The results of this study are presented in the paper.

Irrigation management consists of many components. In this work we review and recommend rainfall forecast performance metrics and adjoint methodologies for the use of predictive weather data within the Colorado State University Water Irrigation Scheduler for Efficient Application (WISE). WISE estimates crop water uses to optimize irrigation scheduling. WISE and its components, input requirements, and related software design issues are discussed. The use of predictive weather allows WISE to consider economic opportunity-costs of decisions to defer water application if rainfall is forecast. These capabilities require an assessment of the system uncertainties and use of weather prediction performance probabilities. Rainfall forecasts and verification performance metrics are reviewed. In addition, model data assimilation methods and adjoint sensitivity concepts are introduced. These assimilation methods make use of observational uncertainties and can link performance metrics to space and time considerations. We conclude with implementation guidance, summaries of available data sources, and recommend a novel adjoint method to address the complex physical linkages and model sensitivities between space and time within the irrigation scheduling physics as a function of soil depth. Such tool improvements can then be used to improve water management decision performance to better conserve and utilize limited water resources for productive use. Editor’s note : This paper is part of the featured series on Optimizing Ogallala Aquifer Water Use to Sustain Food Systems. See the February 2019 issue for the introduction and background to the series.

New conflicts have been arising between energy production and nature conservation, as a consequence of promoting policies for exploiting renewable sources in order to tackle climate change. Assessing the amount of additional land required for renewable energy production has become a crucial aspect of natural resource exploitation. Two research paths are here considered in an attempt to assess this needed additional space in relation to the amount of energy produced by RES (Renewable Energy Source) and the heating demand of a territory. We use open source GIS tools to estimate the energy potential of three energy sources. We examine the relationship between the potential of each energy source and the land use change given by its exploitation in a selected study area. The presented work estimates the potential of the RES, compared this potential with the estimated thermal demand and calculate the amount of land use change required to supply a certain area. A site-specific model is developed for EU28 and estimates the RES potential available trying to minimize the change of the current land-use and the environmental impacts. The analysis considered the technical losses that are required to use the forest biomass, wind and solar energy at regional level. Decision makers can use the analysis resulting from this study to define sustainable policies in terms of renewable energy planning and avoid energy related land use changes and conflicts at local level.

The existence of slums is common to most cities of developing countries. Recent studies have identified that it is important to study and assess the stability of slums as they exhibit vastly different levels of resilience. While many slums are vulnerable to evictions, temporary jobs, and constant migration; few slums can respond and recover from external shocks. In this paper, we present a discrete-choice based agent-based model to investigate inter-slum migration of slum dwellers in Bangalore based on a novel field data from 36 slums in Bangalore. Specifically, we use the model to understand how existing social, economic and environmental situation impacts the choices of slums. The model produces two important insights. First, we find a high social satisfaction applies a stabilizing effect, which means that despite more attractive economic opportunities, the social satisfaction the agents derive from living in a slum is a strong motive to stay. However, given that a lack of opportunities causes emigration, the social satisfaction will decrease as a function of the number of social contacts that move. Further, this cascading effect of emigrating population is more pronounced in Muslim slum households as compared to Hindus. Second, we demonstrate how creating jobs in different occupational categories across social groups may impact the residential choices of slum dwellers. Through this new understanding, policymakers in India can better understand the impacts of their slum management policies ex-ante. With slums that are better managed some of the social (marginalization) and physical (hazardous lands) risks can be mitigated.

Hypervisors used to implement virtual machines (VMs) for infrastructure-as-a-service (IaaS) cloud platforms have undergone continued improvements for the past decade. VM components including CPU, memory, network, and storage I/O have evolved from full software emulation, to paravirtualization, to hardware virtualization. While these innovations have helped reduce performance overhead when simulating a computer, considerable performance loss is still possible in the public cloud from resource contention of co-located VMs. In this paper, we investigate the extent of performance degradation from resource contention by leveraging well-known benchmarks run in parallel across three generations of virtualization hypervisors. Using a Python-based test harness we orchestrate execution of CPU, disk, and network I/O bound benchmarks across up to 48 VMs sharing the same Amazon Web Services dedicated host server. We found that executing benchmarks on hosts with many idle Linux VMs produced unexpected performance degradation. As public cloud users are interested in avoiding resource contention from co-located VMs, we next leveraged our dedicated host performance measurements as independent variables to train models to predict the number of co-resident VMs. We evaluated multiple linear regression and random forest models using test data from independent benchmark runs across 96 vCPU dedicated hosts running up to 48 x 2 vCPU VMs where we controlled VM placements. Multiple linear regression over normalized data achieved R 2 =.942, with mean absolute error of VM co-residency predictions of ±1.61 VMs. We then leveraged our models to infer VM co-residency among a set of 50 VMs on the public cloud, where co-location data is unavailable. Here models cannot be independently verified, but results suggest the relative occupancy level of public cloud hosts enabling users to infer when their VMs reside on busy hosts. Our results characterize how recent hypervisor and hardware advancements are addressing resource contention, while demonstrating the potential to leverage co-located benchmarks for VM co-residency prediction in a public cloud.

One of the most viable options to decarbonise the aviation industry is to operate existing engines and aircrafts through alternative jet fuels (AJFs). The key advantages of these fuels are that they work with existing engine technology, allowing a seamless transition between conventional petroleum jet fuels and more sustainable feedstocks. Lifecycle Assessment models have introduced datasets which attempt to estimate the emissions of AJFs’ process pathways from various feedstocks. To assist with inherent uncertainty in decision making and policy formation in AJFs, a more relativistic uncertainty in the performance of different technology solutions must be assessed to provide an impartial picture of technologies. Here, we propose an integrated multi-criteria decision analysis-based framework to improve performance uncertainty of competing AJF pathways. While existing studies tend to measure effectiveness via cost-benefit analysis or carbon reduction, our proposed framework will provide an in-depth understanding of competing technologies under four dimensions: financial (e.g., capital cost, running cost, feedstock prices; and revenues), environmental (e.g., CO2 emissions savings), technical (e.g., technology maturity; transferability) and social (e.g., social acceptance; wealth and job creation). Compared to standard approaches, our framework can handle data in different forms of uncertainty. Furthermore, we also discuss how different AJFs might be produced more effectively and stress practical points on the need for government and stakeholder integration on the large-scale production of AJFs. By focusing on motives, attitudes and decision making of experts, end-users and stakeholders – rather than merely the pure techno-economic or environmental aspects of AJFs’– this paper makes a new contribution to the field.

Cities are increasingly turning to food policy plans to support goals related to food access, food security, the environment, and economic development. This paper investigates ways that rural farmers, communities, and economies can both support and be supported by metropolitan food-focused initiatives. Specifically, our research question asked what opportunities and barriers exist to developing food policies that support urban food goals, particularly related to local procurement, as well as rural economic development. To address this question, we described and analyzed a meeting of urban stakeholders and larger-scale rural producers related to Colorado's Denver Food Vision and Plan. We documented and explored findings gleaned from a supply chain diagraming and data compilation process that were then used to inform an event that brought together diverse supply chain partners. Three findings stand out. First, facilitating dialog between urban food policymakers and rural producers to understand potential tensions, mitigate such tensions, and capitalize on opportunities is essential. Second, perceptions and expectations surrounding good food are nuanceda timely finding given the number of preferred procurement programs emerging across the county. Third, critical evaluation is needed across a diverse set of value chain strategies (e.g., conventional and alternative distribution) if food policy intends to support heterogeneous producers, their communities, and urban food policy goals.

OMS3 is an environmental modeling framework designed to support and simplify the development of scientific environmental models. It is implemented in Java, a programming language that allows the framework to be flexible and non-invasive. Consequently, Java is the native language for developing OMS-compliant components. However, OMS3 aims to ensure the longevity of old model implementations by providing C/C++ and Fortran bindings that allow for connecting slightly modified legacy environmental software to newly developed Java components. In the recent years, three scientific programming languages drew the modeling community’s attention: R, Python, and NetLogo. They have a flat learning curve, numerous scientific libraries, and duck typing makes them an attractive solution for fast scripting. Furthermore, they have an active developer community that keep releasing and improving open source scientific packages. This is a relevant aspect when it comes to facilitating and speeding up the implementation of scientific algorithms. Therefore, OMS3 integration capabilities have recently been enhanced to provide R, Python, and NetLogo bindings. As a result, multi-language modeling solutions can be tailored to meet the scientific community’s needs. Thanks to the framework’s non-invasiveness, R, Python and NetLogo scripts must only be slightly modified with source code annotations to become OMS-compliant components. The resulting components are nevertheless still executable from within the original environments. This contribution shows two actual applications of the implemented R and Python bindings, the NetLogo implementation is not addressed in this paper. The Regional Urban Growth (RUG) is implemented in R and the TRansportation ANalysis SIMulation System (TRANSIMS) models require the Python Run Time Environment (RTE) module to run. The RUG model is a landscape model capable of evaluating impacts of new regional urban development on surrounding environment and projecting long-term growth-management plans. TRANSIMS is a software suite based on a cellular automata microsimulator which performs regional transportation system analyses. Both model suites are among OMS enabled models for the FICUS project, the “Framework for Integrating the Complexity of Uncertain Systems”. Furthermore, the model application flexibility was enhanced by introducing Docker containers in the workflow to alleviate the burden of complex software management and setup. Keywords​: OMS3; R; Python; RUG; TRANSIMS, FICUS

This research effort is developing a computational framework to support federated models of complex urban systems and enable information support for planning and response in emergency management. Systems analysis has been advocated to support emergency management activities, and there are a number of individual domain models designed to represent various system elements. However, effective implementation of this approach has its challenges. Traditional system analysis is often performed at regional or country scales. Further, information collection tends to be reductionist in process focusing on mission before the operating environment. Thus, there is limited data available to support high resolution urban systems modeling beyond localized areas. However, dense urban environment complexity requires the ability to capture and integrate the interrelationships between subpopulations and infrastructural systems. This system of systems modeling approach supports the analysis of cascading effects through interdependent infrastructure networks and the anticipated impacts on the subpopulations it supports, such as ethnicity, social class, access to transportation, or previously available services. The results are expected to reduce analyst workload by generating geospatial products and systems perspectives of demographic and infrastructure characteristics. We will be presenting an integrated infrastructure system demonstrating the cascading effects of component failure(s) combined with the effects on neighborhood-scale populations. The results are delivered to end-users using a geospatial visualization tool that includes information about the quality of the data products and the ability of the data to support information critical to emergency planning and response.