Inferring Missing Climate Data for Agricultural Planning Using Bayesian Networks

Lara-Estrada, Leonel; Rasche, Livia; Sucar, Luis Enrique; Schneider, Uwe A.

doi:10.3390/land7010004

Cited by 16 publications

(12 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…BN-based models have been applied on several practical problems, such as diagnosis of Alzheimer's disease [76], fault location on distribution feeder [77], human cognition [78], educational testing [79], analysis of resistance pathways against HIV-1 protease inhibitors [80], ovarian cancer diagnosis [81], fault diagnostic system for proton exchange membrane fuel cells [82], information retrieval [83], inferring missing climate data for agricultural planning [84], and predicting protein-protein interactions from genomic data [85]; among others.…”

Section: Figurementioning

confidence: 99%

Black-Box vs. White-Box: Understanding Their Advantages and Weaknesses From a Practical Point of View

2019

View full text Add to dashboard Cite

Nowadays, in the international scientific community of machine learning, there exists an enormous discussion about the use of black-box models or explainable models; especially in practical problems. On the one hand, a part of the community defends that black-box models are more accurate than explainable models in some contexts, like image preprocessing. On the other hand, there exist another part of the community alleging that explainable models are better than black-box models because they can obtain comparable results and also they can explain these results in a language close to a human expert by using patterns. In this paper, advantages and weaknesses for each approach are shown; taking into account a stateof-the-art review for both approaches, their practical applications, trends, and future challenges. This paper shows that both approaches are suitable for solving practical problems, but experts in machine learning need to understand the input data, the problem to solve, and the best way for showing the output data before applying a machine learning model. Also, we propose some ideas for fusing both, explainable and blackbox, approaches to provide better solutions to experts in real-world domains. Additionally, we show one way to measure the effectiveness of the applied machine learning model by using expert opinions jointly with statistical methods. Throughout this paper, we show the impact of using explainable and black-box models on the security and medical applications. INDEX TERMS Black-box, white-box, explainable artificial intelligence, deep learning.

show abstract

Section: Figurementioning

confidence: 99%

Black-Box vs. White-Box: Understanding Their Advantages and Weaknesses From a Practical Point of View

2019

View full text Add to dashboard Cite

show abstract

“…Equations (27)–(29) respectively represent the metrics:

MAE = \frac{\sum_{t = 1}^{T} ∣ {\overset{false^}{y}}_{t} - y_{t} ∣}{T}

RMSE = \sqrt{\frac{\sum_{t = 1}^{T} {((), {\overset{false^}{y}}_{t} - y_{t})}^{2}}{T}}

SMAPE = \frac{\sum_{t = 1}^{T} (||, ((), {\overset{false^}{y}}_{t} - y_{t}) / y)}{T} \times 100

where

\overset{y}{true} = \sum_{t = 1}^{T} y_{t} / T

{\overset{false^}{y}}_{t}

and y t are the imputed and actual values for time t and T is the length of the missing data in the time series. The MAE and RMSE are useful performance indicators (McCandless et al ., ; Kanda et al ., ; Lara‐Estrada et al ., ). Both the MAE and RMSE range from 0 to +∞, and lower values indicate high levels of agreement between observed and estimated values.…”

Section: Model Performance Evaluationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…Climatic conditions such as precipitation, temperature, humidity, wind speed, wind gust and sea level pressure have been used over time in many meteorological, energy application, agricultural, ecological and hydrological studies (Firat et al, 2012;Xu et al, 2013;Lara-Estrada et al, 2018). Weather stations across the world continue to record and monitor various climatic parameters for climate classification, planning, modelling and management purposes (Firat et al, 2012;Lara-Estrada et al, 2018). In recent years, the threats of global warming and climate change (World Bank, 2012) have sparked a resurgent interest in the analysis and inference of climatic variables and related subjects in the natural, social and political sciences.…”

Section: Introductionmentioning

confidence: 99%

“…In a comparative study on the estimation of missing values in daily temperature and precipitation data, Kanda et al (2018) reported that multiple regression using the least absolute deviation performed best based on four performance indicators, namely mean absolute error (MAE), root mean squared error (RMSE), coefficient of efficiency and skill score. Other methods such as the regularized EM algorithm (Schneider 2001), the Fourier fit, the artificial neural network (McCandless et al 2011;Kashani and Dinpasho, 2012), the multilayer perceptron neural network, the EM-Markov chain Monte Carlo (Yozgatligil et al, 2013) and the Bayesian network (Lara-Estrada et al, 2018) have been applied in the imputation of missing observations in daily and monthly precipitation, temperature and humidity data.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Missing data imputation of high‐resolution temporal climate time series data

Afrifa-Yamoah

Mueller

Taylor³

et al. 2020

Meteorological Applications

View full text Add to dashboard Cite

Analysis of high‐resolution data offers greater opportunity to understand the nature of data variability, behaviours, trends and to detect small changes. Climate studies often require complete time series data which, in the presence of missing data, means imputation must be undertaken. Research on the imputation of high‐resolution temporal climate time series data is still at an early phase. In this study, multiple approaches to the imputation of missing values were evaluated, including a structural time series model with Kalman smoothing, an autoregressive integrated moving average (ARIMA) model with Kalman smoothing and multiple linear regression. The methods were applied to complete subsets of data from 12 month time series of hourly temperature, humidity and wind speed data from four locations along the coast of Western Australia. Assuming that observations were missing at random, artificial gaps of missing observations were studied using a five‐fold cross‐validation methodology with the proportion of missing data set to 10%. The techniques were compared using the pooled mean absolute error, root mean square error and symmetric mean absolute percentage error. The multiple linear regression model was generally the best model based on the pooled performance indicators, followed by the ARIMA with Kalman smoothing. However, the low error values obtained from each of the approaches suggested that the models competed closely and imputed highly plausible values. To some extent, the performance of the models varied among locations. It can be concluded that the modelling approaches studied have demonstrated suitability in imputing missing data in hourly temperature, humidity and wind speed data and are therefore recommended for application in other fields where high‐resolution data with missing values are common.

show abstract

Bayesian Networks: Learning

Sucar

2020

Probabilistic Graphical Models

View full text Add to dashboard Cite

Inferring Missing Climate Data for Agricultural Planning Using Bayesian Networks

Cited by 16 publications

References 51 publications

Black-Box vs. White-Box: Understanding Their Advantages and Weaknesses From a Practical Point of View

Black-Box vs. White-Box: Understanding Their Advantages and Weaknesses From a Practical Point of View

Missing data imputation of high‐resolution temporal climate time series data

Bayesian Networks: Learning

Contact Info

Product

Resources

About