scholarly journals Genetics-inspired data-driven approaches explain and predict crop performance fluctuations attributed to changing climatic conditions

2022 ◽  
Author(s):  
Xianran Li ◽  
Tingting Guo ◽  
Guihua Bai ◽  
Zhiwu Zhang ◽  
Deven See ◽  
...  
Keyword(s):  
Climatic Conditions ◽  
Data Driven ◽  
Crop Performance

scholarly journals A Data-Driven Surrogate Approach for the Temporal Stability Forecasting of Vegetation Covered Dikes

Water ◽  
2021 ◽  
Vol 13 (1) ◽  
pp. 107
Author(s):  
Elahe Jamalinia ◽  
Faraz S. Tehrani ◽  
Susan C. Steele-Dunne ◽  
Philip J. Vardon
Keyword(s):  
Numerical Simulation ◽  
Water Flux ◽  
Temporal Stability ◽  
Synthetic Data ◽  
Climatic Conditions ◽  
Training Data ◽  
Data Driven ◽  
Data Set ◽  
Surface Cracking ◽  
Real Time Analysis

Climatic conditions and vegetation cover influence water flux in a dike, and potentially the dike stability. A comprehensive numerical simulation is computationally too expensive to be used for the near real-time analysis of a dike network. Therefore, this study investigates a random forest (RF) regressor to build a data-driven surrogate for a numerical model to forecast the temporal macro-stability of dikes. To that end, daily inputs and outputs of a ten-year coupled numerical simulation of an idealised dike (2009–2019) are used to create a synthetic data set, comprising features that can be observed from a dike surface, with the calculated factor of safety (FoS) as the target variable. The data set before 2018 is split into training and testing sets to build and train the RF. The predicted FoS is strongly correlated with the numerical FoS for data that belong to the test set (before 2018). However, the trained model shows lower performance for data in the evaluation set (after 2018) if further surface cracking occurs. This proof-of-concept shows that a data-driven surrogate can be used to determine dike stability for conditions similar to the training data, which could be used to identify vulnerable locations in a dike network for further examination.

scholarly journals Data-driven yield projections suggest large opportunities to improve Europe’s soybean self-sufficiency under climate change

2020 ◽  
Author(s):  
Nicolas Guilpart ◽  
Toshichika Iizumi ◽  
David Makowski
Keyword(s):  
Climatic Conditions ◽  
Future Climate ◽  
Environmental Benefits ◽  
Data Driven ◽  
Machine Learning Techniques ◽  
Soybean Production ◽  
Self Sufficiency ◽  
Learning Techniques ◽  
Rcp 8.5 ◽  
Cultivated Species

AbstractCurrently, demand for soybean in Europe is mostly fulfilled by imports. However, soybean-growing areas across Europe have been rapidly increasing in response to a rising demand for locally-produced, non-GM soybean in recent years. This raises questions about the suitability of European agro-climatic conditions for soybean production. We used data-driven relationships between climate and soybean yield derived from machine-learning techniques to make yield projections under current and future climate with moderate (RCP 4.5) to intense (RCP 8.5) warming, up to the 2050s and 2090s time horizons. Results suggest that a self-sufficiency level of 50% (100%) would be achievable in Europe under historical and future climate if 4-5% (9-12%) of the current European cropland is dedicated to soybean production. The associated increase in soybean area in Europe would bring environmental benefits, with a potential decrease of nitrogen fertilizer use in Europe by 5-8% (13-18%) and a possible reduction of deforestation in biodiversity hotspots in South America. However, it would also lead to an important reduction in the production of other cultivated species in Europe (e.g. cereals) and a potential increase in the use of irrigation water.

Information systems for crop performance data

2006 ◽  
Vol 86 (3) ◽  
pp. 647-662 ◽  
Author(s):  
N. A. Tinker ◽  
W. Yan
Keyword(s):  
Information Systems ◽  
Climatic Conditions ◽  
Performance Data ◽  
Current Status ◽  
Biological Research ◽  
Growth Stages ◽  
Economic Traits ◽  
Multiple Sources ◽  
Phenotypic Data ◽  
Crop Performance

An increased need for efficient storage and retrieval of crop performance data is driven by a desire to increase the value of crop performance tests, opportunities in crop modelling, opportunities to facilitate cross planning, opportunities to discover genes that affect economic traits, and data mining applications that require better integration of data from multiple sources. Thus, an increased number of stakeholders need access to crop data that are current, accurate, and complete. There is also a growing sophistication and awareness of the role and capabilities of modern informatics techniques in biological research – an area that has become known as “bioinformatics”. Bioinformatics, in partnership with statistics, can play a vital role in increasing the value of crop performance data. However, much of this role remains to be developed and adopted by the communities that gather and use these data. Part of the challenge is that phenotypic data are complex, and extensive information about the context under which the data were collected is required. This can include information about experimental design, soil and climatic conditions, treatments applied, germplasm tested, plant growth stages, and traits measured. If context is neglected, data are useless, but if context is overly complex, it may be ignored or used improperly. Several solutions have been developed to address these needs. These include commercial software packages, open-source collaborations, and a new application developed by the authors. Each solution has strengths and weaknesses, and each addresses different types of needs. This review will discuss the motivations for developing and using crop information systems, the current status and availability of crop information systems, and the challenges that must be met to achieve future potential. Key words: Bioinformatics, database, software, statistics, ontology, variety trial

scholarly journals Robustness of Process-Based versus Data-Driven Modeling in Changing Climatic Conditions

2020 ◽  
Vol 21 (9) ◽  
pp. 1929-1944 ◽  
Author(s):  
Sungmin O ◽  
Emanuel Dutra ◽  
Rene Orth
Keyword(s):  
Land Surface ◽  
Short Term Memory ◽  
Climatic Conditions ◽  
Data Driven ◽  
Balance Model ◽  
Surface Model ◽  
Climate Projections ◽  
Spatial And Temporal Variability ◽  
Split Sample ◽  
Physically Based

AbstractFuture climate projections require Earth system models to simulate conditions outside their calibration range. It is therefore crucial to understand the applicability of such models and their modules under transient conditions. This study assesses the robustness of different types of models in terms of rainfall–runoff modeling under changing conditions. In particular, two process-based models and one data-driven model are considered: 1) the physically based land surface model of the European Centre for Medium-Range Weather Forecasts, 2) the conceptual Simple Water Balance Model, and 3) the Long Short-Term Memory-Based Runoff model. Using streamflow data from 161 catchments across Europe, a differential split-sample test is performed, i.e., models are calibrated within a reference period (e.g., wet years) and then evaluated during a climatically contrasting period (e.g., drier years). Models show overall performance loss, which generally increases the more conditions deviate from the reference climate. Further analysis reveals that the models have difficulties in capturing temporal shifts in the hydroclimate of the catchments, e.g., between energy- and water-limited conditions. Overall, relatively high robustness is demonstrated by the physically based model. This suggests that improvements of physics-based parameterizations can be a promising avenue toward reliable climate change simulations. Further, our study illustrates that comparison across process-based and data-driven models is challenging due to their different nature. While we find rather low robustness of the data-driven model in our particular split-sample setup, this must not apply generally; by contrast, such model schemes have great potential as they can learn diverse conditions from observed spatial and temporal variability both at the same time to yield robust performance.

scholarly journals Optimized cultivar deployment improves the efficiency and stability of sunflower crop production at national scale

2020 ◽  
Author(s):  
Pierre Casadebaig ◽  
Arnaud Gauffreteau ◽  
Amélia Landré ◽  
Nicolas B. Langlade ◽  
Emmanuelle Mestries ◽  
...  
Keyword(s):  
Plant Breeding ◽  
Crop Production ◽  
Management Practices ◽  
Genetic Material ◽  
Optimization Methods ◽  
Climatic Conditions ◽  
Soil Conditions ◽  
Management Options ◽  
Crop Performance ◽  
Stress Patterns

AbstractPlant breeding programs design new crop cultivars which, while developed for distinct populations of environments, are nevertheless grown over large areas during their careers. Over its cultivation area, the crop is exposed to highly diverse stress patterns caused by climatic uncertainty and multiple management options, which often leads to decreased expected crop performance.In this study, we aim is to assess how finer spatial management of genetic resources could reduce the genotype-phenotype mismatch in cropping environments and ultimately improve the efficiency and stability of crop production. We used modeling and simulation to predict the crop performance resulting from the interaction between cultivar growth and development, climate and soil conditions, and management practices. We designed a computational experiment that evaluated the performance of a collection of commercial sunflower cultivars in a realistic population of cropping conditions in France, built from extensive agricultural surveys. Distinct farming locations that shared similar simulated abiotic stress patterns were clustered together to specify environment types. Optimization methods were then used to search for cultivars × environments combinations that lead to increased yield expectations.Results showed that a single cultivar choice adapted to the most frequent environment-type in the population is a robust strategy. However, the relevance of cultivar recommendations to specific locations was gradually increasing with the knowledge of pedo-climatic conditions. We argue that this approach while being operational on current genetic material could act synergistically with plant breeding as more diverse material could enable access to cultivars with distinctive traits, more adapted to specific conditions.

scholarly journals An Introduction to the Hyperspace of Hargreaves-Samani Reference Evapotranspiration

2018 ◽  
Vol 10 (11) ◽  
pp. 4277
Author(s):  
Naim Haie ◽  
Rui Pereira ◽  
Haw Yen
Keyword(s):  
Climate Change ◽  
Reference Evapotranspiration ◽  
Climatic Conditions ◽  
Climatic Variables ◽  
Data Driven ◽  
Empirical Coefficient ◽  
The World ◽  
Mathematical Equations ◽  
The Common ◽  
Watershed Processes

Climate change has been shown to directly influence evapotranspiration, which is one of the crucial watershed processes. The common approach to its calculation is via mathematical equations, such as 1985 Hargreaves-Samani (HS85). It computes reference evapotranspiration (ETo) through three climatic variables and one constant: RA (extra-terrestrial radiation), TC (mean temperature), TR (temperature range) and KR (empirical coefficient). To make HS85 more accurate, one of its authors proposed an equation for KR as a function of TR in 2000 (HS00). Both models are 4D and their internal behaviours are difficult to understand, hence, the data driven applications prevalent among experts and managers. In this study, we introduce an innovative research by trying to respond to two questions. What are the relationships between TC and TR? What are the internal patterns of HS hyperspace (4D domain) and the changes in ETo possibilities of the two models? In the proposed approach, thresholds for the four variables are utilized to cover majority of the agroclimatic situations in the world and the hyperspace is discretized with more than 50,000 calculation nodes. The ETo results show that under various climatic conditions, the behaviour of HS is nonlinear (more for HS00) leading to an increased uncertainty particularly for data driven applications. TC and TR show patterns useful for regions with less data.

Sign in / Sign up

Export Citation Format

Share Document