Prediction of N2O emission from local information with Random Forest

Philibert, Aurore; Loyce, Chantal; Makowski, David

doi:10.1016/j.envpol.2013.02.019

Cited by 72 publications

(38 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As recommended by Philibert et al (2013), the potential for publication bias was investigated and sensitivity analyses were conducted to examine how individual observations influenced weighted mean effect sizes. Because sampling variances were not available for individual observations, funnel plots were created for each crop category using approximated standard errors using the "metafor" package in R (Viechtbauer, 2010).…”

Section: Discussionmentioning

confidence: 99%

When does no-till yield more? A global meta-analysis

Pittelkow

Linquist

Lundy

et al. 2015

Field Crops Research

661

401

View full text Add to dashboard Cite

a b s t r a c tNo-till agriculture represents a relatively widely adopted management system that aims to reduce soil erosion, decrease input costs, and sustain long-term crop productivity. However, its impacts on crop yields are variable, and an improved understanding of the factors limiting productivity is needed to support evidence-based management decisions. We conducted a global meta-analysis to evaluate the influence of various crop and environmental variables on no-till relative to conventional tillage yields using data obtained from peer-reviewed publications (678 studies with 6005 paired observations, representing 50 crops and 63 countries). Side-by-side yield comparisons were restricted to studies comparing conventional tillage to no-till practices in the absence of other cropping system modifications. Crop category was the most important factor influencing the overall yield response to no-till followed by aridity index, residue management, no-till duration, and N rate. No-till yields matched conventional tillage yields for oilseed, cotton, and legume crop categories. Among cereals, the negative impacts of no-till were smallest for wheat (−2.6%) and largest for rice (−7.5%) and maize (−7.6%). No-till performed best under rainfed conditions in dry climates, with yields often being equal to or higher than conventional tillage practices. Yields in the first 1-2 years following no-till implementation declined for all crops except oilseeds and cotton, but matched conventional tillage yields after 3-10 years except for maize and wheat in humid climates. Overall, no-till yields were reduced by 12% without N fertilizer addition and 4% with inorganic N addition. Our study highlights factors contributing to and/or decreasing no-till yield gaps and suggests that improved targeting and adaptation, possibly including additional system modifications, are necessary to optimize no-till performance and contribute to food production goals. In addition, our results provide a basis for conducting trade-off analyses to support the development of no-till crop management and international development strategies based on available scientific evidence.

show abstract

Section: Discussionmentioning

confidence: 99%

When does no-till yield more? A global meta-analysis

Pittelkow

Linquist

Lundy

et al. 2015

Field Crops Research

661

401

View full text Add to dashboard Cite

show abstract

“…Random forest analysis of Big Data sets has also been used to investigate other important issues in agriculture such as nitrous oxide (N 2 O) emissions (Philibert et al 2013), leaf nitrogen levels (Abdel-Rahman et al 2013), and drought forecasting (Chen et al 2012). Abdel-Rahman et al (2013) used random forest regression to build predictive models of sugarcane leaf nitrogen levels from hyperspectral satellite images, while Philibert et al (2013) were able to identify nitrogen fertilization, crop type, and experiment duration as the most important predictor variables of N 2 O emissions.…”

Section: Introductionmentioning

confidence: 99%

“…Abdel-Rahman et al (2013) used random forest regression to build predictive models of sugarcane leaf nitrogen levels from hyperspectral satellite images, while Philibert et al (2013) were able to identify nitrogen fertilization, crop type, and experiment duration as the most important predictor variables of N 2 O emissions. Saussure et al (2015) incorporated random forests as part of a data processing framework to develop preventive solutions for the sustainable control of wireworms and Everingham et al (2007b) successfully used random forests to classify sugarcane variety and the number of times the sugarcane has been harvested and allowed to regrow.…”

Section: Introductionmentioning

confidence: 99%

Accurate prediction of sugarcane yield using a random forest algorithm

Everingham

Sexton

Skocaj

et al. 2016

Agron. Sustain. Dev.

262

View full text Add to dashboard Cite

Foreknowledge about sugarcane crop size can help industry members make more informed decisions. There exists many different combinations of climate variables, seasonal climate prediction indices, and crop model outputs that could prove useful in explaining sugarcane crop size. A data mining method like random forests can cope with generating a prediction model when the search space of predictor variables is large. Research that has investigated the accuracy of random forests to explain annual variation in sugarcane productivity and the suitability of predictor variables generated from crop models coupled with observed climate and seasonal climate prediction indices is limited. Simulated biomass from the APSIM (Agricultural Production Systems sIMulator) sugarcane crop model, seasonal climate prediction indices and observed rainfall, maximum and minimum temperature, and radiation were supplied as inputs to a random forest classifier and a random forest regression model to explain annual variation in regional sugarcane yields at Tully, in northeastern Australia. Prediction models were generated on 1 September in the year before harvest, and then on 1 January and 1 March in the year of harvest, which typically runs from June to November. Our results indicated that in 86.36 % of years, it was possible to determine as early as September in the year before harvest if production would be above the median. This accuracy improved to 95.45 % by January in the year of harvest. The R-squared of the random forest regression model gradually improved from 66.76 to 79.21 % from September in the year before harvest through to March in the same year of harvest. All three sets of variables-(i) simulated biomass indices, (ii) observed climate, and (iii) seasonal climate prediction indices-were typically featured in the models at various stages. Better crop predictions allows farmers to improve their nitrogen management to meet the demands of the new crop, mill managers could better plan the mill's labor requirements and maintenance scheduling activities, and marketers can more confidently manage the forward sale and storage of the crop. Hence, accurate yield forecasts can improve industry sustainability by delivering better environmental and economic outcomes.

show abstract

“…Chen and Ishwaran (2012) utilized RF for high dimensional genomic data analysis in order to detect associations and detection of epistasis [40]. RF was also used for environmental engineering purposes by Philibert et al (2013). Here, they have shown that not only RF managed to yield good N20 predictions given a significant proportion of missing data, but it also identified important input variables for such prediction such as the nitrogen rate, type of crop, and experiment duration [41].…”

Section: Random Forestsmentioning

confidence: 99%

“…RF was also used for environmental engineering purposes by Philibert et al (2013). Here, they have shown that not only RF managed to yield good N20 predictions given a significant proportion of missing data, but it also identified important input variables for such prediction such as the nitrogen rate, type of crop, and experiment duration [41]. Smith et al (2010) had used RF in order to track bacterial sources [42].…”

Section: Random Forestsmentioning

confidence: 99%

Strategic Well Test Planning Using Random Forest

2014

View full text Add to dashboard Cite

Optimizing a huge oilfield with hundreds of wells would involve thorough analysis. Here, the performance of a subset of those wells might be a critical factor. Therefore, it is important to obtain accurate information on that subset.Obtaining accurate information on an individual well is usually done via a proper well test analysis. Although performing a well test is relatively expensive, it can provide important information such as the skin, reservoir pressure (i.e. BHP), permeability, and nearby faults.In this study, we would like emphasize on the measurement of BHP. This emphasis is chosen due to the fact that the BHP from a subset of all wells can be a contributing factor towards the field oil recovery factor. Hence, the objective of this study is to find that subset of wells based on uncertainty studies conducted via reservoir simulations. Here, the uncertainty study involves performing 100 Latin Hypercube Monte Carlo (LHMC) sampling of the reservoir simulation input parameters. For each of the 100 runs, the uncertain input parameters and simulated BHP values/trends for each well are recorded. Thus, a dataset consists of the input parameters, simulated BHP for each well, and the field oil recovery factor as columns will be generated.The random forest (RF) algorithm was implemented in order to find the subset of wells mentioned. RF algorithm is simply a collection of decision trees (DT), where the results generated by RF were obtained by using a voting mechanism among the trees involved. Several trees were sampled from the generated forest, and reveal interactions between the monitored BHP value/trend with other parameters. Combination of LHMC and RF can also be seen a global approach to sensitivity analysis, since RF can reveal the rank of importance of the RF's independent variables based on a collection of uncertainty runs.In the exploration and production (E&P) applications, DT has been used extensively; appraising, real option valuation selecting an artificial lift method, predicting permeabilities and detecting fracture corridors . However, to the best of the authors' knowledge, RF had never been implemented in any E&P activities, particularly in strategic well test planning.

show abstract

Prediction of N2O emission from local information with Random Forest

Cited by 72 publications

References 36 publications

When does no-till yield more? A global meta-analysis

When does no-till yield more? A global meta-analysis

Accurate prediction of sugarcane yield using a random forest algorithm

Strategic Well Test Planning Using Random Forest

Contact Info

Product

Resources

About