Search

Spatially explicit information on land cover (LC) is commonly derived using remote sensing, but the lack of training data still remains a major challenge for producing accurate LC products. Here, we develop a computer vision methodology to extract LC information from photos from the Land Use-Land Cover Area Frame Survey (LUCAS). Given the large number of photographs available and the comprehensive spatial coverage, the objective is to show how the automatic classification of photos could be used to develop reference data sets for training and validation of LC products as well as other purposes. We first selected a representative sample of 1120 photos covering eight major LC types across the European Union. We then applied semantic segmentation to these photos using a neural network (Deeplabv3+) trained with the ADE20k dataset. For each photo, we extracted the original LC identified by the LUCAS surveyor, the segmented objects, and the pixel count for each ADE20k class. Using the latter as input features, we then trained a Random Forest model to classify the LC of the photo. Examining the relationship between the objects/features extracted by Deeplabv3+ and the LC labels provided by the LUCAS surveyors demonstrated how the LC classes can be decomposed into multiple objects, highlighting the complexity of LC classification from photographs. The results of the classification show a mean F1 Score of 89%, increasing to 93% when the Wetland class is not considered. Based on these results, this approach holds promise for the automated retrieval of LC information from the rich source of LUCAS photographs as well as the increasing number of geo-referenced photos now becoming available through social media and sites like Mapillary or Google Street View.

The following data set shows the results of the 2018 FotoQuest Go Europe crowdsourcing campaign. This land cover and land use change monitoring citizen science campaign ran during the summer of 2018 and asked participants across Europe to use the FotoQuest mobile application and visit specific locations across the continent. The locations were taken from the 2015 LUCAS campaign, a 3-year land use and land cover survey undertaken by EUROSTAT. The participants were awarded between 1 and 3 euros for every location visited and up to 30 euros in special challenge locations. There was also a feedback mechanism that allowed IIASA researchers to review the each submitted quest, approve or reject it, and send feedback to the participants. The campaign and results are described in detail in the Land journal paper ?Crowdsourcing LUCAS: Citizens Generating Reference Land Cover and Land Use Data with a Mobile App? (Laso Bayas et al 2020) freely accessible here: https://doi.org/10.3390/land9110446 . The word file accompanying the data describes all variables contained in the FotoQuest Go Europe 2018 data set.

Regional monitoring, reporting and verification of soil organic carbon change occurring in managed cropland are indispensable to support carbon-related policies. Rapidly evolving gridded agronomic models can facilitate these efforts throughout Europe. However, their performance in modelling soil carbon dynamics at regional scale is yet unexplored. Importantly, as such models are often driven by large-scale inputs, they need to be benchmarked against field experiments. We elucidate the level of detail that needs to be incorporated in gridded models to robustly estimate regional soil carbon dynamics in managed cropland, testing the approach for regions in the Czech Republic. We first calibrated the biogeochemical Environmental Policy Integrated Climate (EPIC) model against long-term experiments. Subsequently, we examined the EPIC model within a top-down gridded modelling framework constructed for European agricultural soils from Europe-wide datasets and regional land-use statistics. We explored the top-down, as opposed to a bottom-up, modelling approach for reporting agronomically relevant and verifiable soil carbon dynamics. In comparison with a no-input baseline, the regional EPIC model suggested soil carbon changes (~0.1–0.5 Mg C ha−1 y−1) consistent with empirical-based studies for all studied agricultural practices. However, inaccurate soil information, crop management inputs, or inappropriate model calibration may undermine regional modelling of cropland management effect on carbon since each of the three components carry uncertainty (~0.5–1.5 Mg C ha−1 y−1) that is substantially larger than the actual effect of agricultural practices relative to the no-input baseline. Besides, inaccurate soil data obtained from the background datasets biased the simulated carbon trends compared to observations, thus hampering the model's verifiability at the locations of field experiments. Encouragingly, the top-down agricultural management derived from regional land-use statis

In recent years, the crop growth modeling community invested immense effort into high resolution global simulations estimating inter alia the impacts of projected climate change. The demand for computing resources in this context is high and expressed in processor core-years per one global simulation, implying several crops, management systems, and a several decades time span for a single climatic scenario. The anticipated need to model a richer set of alternative management options and crop varieties would increase the processing capacity requirements even more, raising the looming issue of computational efficiency. While several publications report on the successful application of the original field-scale crop growth model EPIC (Environmental Policy Integrated Climate) for running on modern supercomputers, the related performance improvement issues and, especially, associated trade-offs have only received, so far, limited coverage. This paper provides a comprehensive view on the principles of the EPIC setup for parallel computations and, for the first time, on those specific to heterogeneous compute clusters that are comprised of desktop computers utilizing their idle time to carry out massive computations. The suggested modification of the core EPIC model allows for a dramatic performance increase (order of magnitude) on a compute cluster that is powered by the open-source high-throughput computing software framework HTCondor.

There are many new land use and land cover (LULC) products emerging yet there is still a lack of in situ data for training, validation, and change detection purposes. The LUCAS (Land Use Cover Area frame Sample) survey is one of the few authoritative in situ field campaigns, which takes place every three years in European Union member countries. More recently, a study has considered whether citizen science and crowdsourcing could complement LUCAS survey data, e.g., through the FotoQuest Austria mobile app and crowdsourcing campaign. Although the data obtained from the campaign were promising when compared with authoritative LUCAS survey data, there were classes that were not well classified by the citizens. Moreover, the photographs submitted through the app were not always of sufficient quality. For these reasons, in the latest FotoQuest Go Europe 2018 campaign, several improvements were made to the app to facilitate interaction with the citizens contributing and to improve their accuracy in LULC identification. In addition to extending the locations from Austria to Europe, a change detection component (comparing land cover in 2018 to the 2015 LUCAS photographs) was added, as well as an improved LC decision tree. Furthermore, a near real-time quality assurance system was implemented to provide feedback on the distance to the target location, the LULC classes chosen and the quality of the photographs. Another modification was a monetary incentive scheme in which users received between 1 to 3 Euros for each successfully completed quest of sufficient quality. The purpose of this paper is to determine whether citizens can provide high quality in situ data on LULC through crowdsourcing that can complement LUCAS. We compared the results between the FotoQuest campaigns in 2015 and 2018 and found a significant improvement in 2018, i.e., a much higher match of LC between FotoQuest Go Europe and LUCAS. As shown by the cost comparisons with LUCAS, FotoQuest can complement LUC

Wheat grain protein concentration is an important determinant of wheat quality for human nutrition that is often overlooked in efforts to improve crop production. We tested and applied a 32-multi-model ensemble to simulate global wheat yield and quality in a changing climate. Potential benefits of elevated atmospheric CO2 concentration by 2050 on global wheat grain and protein yield are likely to be negated by impacts from rising temperature and changes in rainfall, but with considerable disparities between regions. Grain and protein yields are expected to be lower and more variable in most low-rainfall regions, with nitrogen availability limiting growth stimulus from elevated CO2 . Introducing genotypes adapted to warmer temperatures (and also considering changes in CO2 and rainfall) could boost global wheat yield by 7% and protein yield by 2%, but grain protein concentration would be reduced by -1.1 percentage points, representing a relative change of -8.6%. Climate change adaptations that benefit grain yield are not always positive for grain quality, putting additional pressure on global wheat production.

Efforts to limit global warming to below 2°C in relation to the pre-industrial level are under way, in accordance with the 2015 Paris Agreement. However, most impact research on agriculture to date has focused on impacts of warming >2°C on mean crop yields, and many previous studies did not focus sufficiently on extreme events and yield interannual variability. Here, with the latest climate scenarios from the Half a degree Additional warming, Prognosis and Projected Impacts (HAPPI) project, we evaluated the impacts of the 2015 Paris Agreement range of global warming (1.5°C and 2.0°C warming above the pre-industrial period) on global wheat production and local yield variability. A multi-crop and multi-climate model ensemble over a global network of sites developed by the Agricultural Model Intercomparison and Improvement Project (AgMIP) for Wheat was used to represent major rainfed and irrigated wheat cropping systems. Results show that projected global wheat production will change by -2.3% to 7.0% under the 1.5 °C scenario and -2.4% to 10.5% under the 2.0 °C scenario, compared to a baseline of 1980-2010, when considering changes in local temperature, rainfall and global atmospheric CO2 concentration, but no changes in management or wheat cultivars. The projected impact on wheat production varies spatially; a larger increase is projected for temperate high rainfall regions than for moderate hot low rainfall and irrigated regions. Grain yields in warmer regions are more likely to be reduced than in cooler regions. Despite mostly positive impacts on global average grain yields, the frequency of extremely low yields (bottom 5 percentile of baseline distribution) and yield inter-annual variability will increase under both warming scenarios for some of the hot growing locations, including locations from the second largest global wheat producer -India, which supplies more than 14% of global wheat. The projected global impact of warming <2°C on wheat production are therefor

Wheat grain protein concentration is an important determinant of wheat quality for human nutrition that is often overlooked in efforts to improve crop production. We tested and applied a 32‐multi‐model ensemble to simulate global wheat yield and quality in a changing climate. Potential benefits of elevated atmospheric CO2 concentration by 2050 on global wheat grain and protein yield are likely to be negated by impacts from rising temperature and changes in rainfall, but with considerable disparities between regions. Grain and protein yields are expected to be lower and more variable in most low‐rainfall regions, with nitrogen availability limiting growth stimulus from elevated CO2. Introducing genotypes adapted to warmer temperatures (and also considering changes in CO2 and rainfall) could boost global wheat yield by 7% and protein yield by 2%, but grain protein concentration would be reduced by −1.1 percentage points, representing a relative change of −8.6%. Climate change adaptations that benefit grain yield are not always positive for grain quality, putting additional pressure on global wheat production.

Global and regional scale agricultural monitoring systems aim to provide up-to-date information regarding food production to different actors and decision makers in support of global and national food security. To help reduce price volatility of the kind experienced between 2007 and 2011, a global system of agricultural monitoring systems is needed to ensure the coordinated flow of information in a timely manner for early warning purposes. A number of systems now exist that fill this role. This paper provides an overview of the eight main global and regional scale agricultural monitoring systems currently in operation and compares them based on the input data and models used, the outputs produced and other characteristics such as the role of the analyst, their interaction with other systems and the geographical scale at which they operate. Despite improvements in access to high resolution satellite imagery over the last decade and the use of numerous remote-sensing based products by the different systems, there are still fundamental gaps. Based on a questionnaire, discussions with the system experts and the literature, we present the main gaps in the data and in the methods. Finally, we propose some recommendations for addressing these gaps through ongoing improvements in remote sensing, harnessing new and innovative data streams and the continued sharing of more and more data.