Abstract

Dewpoint temperature, the temperature at which water vapor in the air will condense into liquid, can be useful in estimating frost, fog, snow, dew, evapotranspiration, and other meteorological variables. The goal of this study was to use artificial neural networks (ANNs) to predict dewpoint temperature from 1 to 12 h ahead using prior weather data as inputs. This study explores using three-layer backpropagation ANNs and weather data combined for three years from 20 locations in Georgia, United States, to develop general models for dewpoint temperature prediction anywhere within Georgia. Specific objectives included the selection of the important weather-related inputs, the setting of ANN parameters, and the selection of the duration of prior input data. An iterative search found that, in addition to dewpoint temperature, important weather-related ANN inputs included relative humidity, solar radiation, air temperature, wind speed, and vapor pressure. Experiments also showed that the best models included 60 nodes in the ANN hidden layer, a ±0.15 initial range for the ANN weights, a 0.35 ANN learning rate, and a duration of prior weather-related data used as inputs ranging from 6 to 30 h based on the lead time. The evaluation of the final models with weather data from 20 separate locations and for a different year showed that the 1-, 4-, 8-, and 12-h predictions had mean absolute errors (MAEs) of 0.550°, 1.234°, 1.799°, and 2.280°C, respectively. These final models predicted dewpoint temperature adequately using previously unseen weather data, including difficult freeze and heat stress extremes. These predictions are useful for decisions in agriculture because dewpoint temperature along with air temperature affects the intensity of freezes and heat waves, which can damage crops, equipment, and structures and can cause injury or death to animals and humans.

1. Introduction

Dewpoint temperature is the temperature at which water vapor in the air will condense into dew or water droplets given that the air pressure remains constant. Alternatively, it can be defined as the temperature at which the saturation vapor pressure and actual vapor pressure are equal (Merva 1975). Dewpoint temperature coupled with relative humidity can be used to determine the amount of moisture in the air. Dewpoint temperature is a good estimate of near-surface humidity, thus the dewpoint temperature can affect the stomatal closure in plants, where low humidity can reduce the productivity of the plants (Kimball et al. 1997). When the surface air temperature drops to the level of the dewpoint temperature, dew forms. Especially in arid regions that have infrequent rainfall, the dew can be essential to plant survival (Agam and Berliner 2006).

Many agronomical, ecological, hydrological, and climatological models require dewpoint temperature as an input to estimate evapotranspiration (Hubbard et al. 2003). Dewpoint temperature may also be used to calculate actual vapor pressure or estimate relative humidity (Mahmood and Hubbard 2005). Dewpoint temperature coupled with wet-bulb temperature can be used to calculate critical-damage air temperature for specific crops, allowing producers to determine the potential for a frost to damage those crops (Snyder and de Melo-Abreu 2005). Heat waves, which cause damage and take the lives of people and animals, are intensified by high dewpoint temperatures (Sandstrom et al. 2004). These studies suggest that a non-location-specific dewpoint temperature prediction would be helpful for those in rural areas where fewer weather predictions are made, and there are more crops and livestock. A study by Robinson (2000) proposed that the dewpoint temperature in the United States is slowly increasing over time and, therefore, could be an important weather variable for studies on long-term climate change.

Hubbard et al. (2003) developed a regression model for estimating the daily average dewpoint temperature, using the daily mean, minimum, and maximum air temperature as inputs. Their research used 14 yr of data for six cities from South Dakota, Nebraska, Colorado, and Kansas in the United States. Their regression equation based on multiple cities was more accurate than the regression equations for each of the individual cities, with a mean absolute error (MAE) of 2.2°C for the most accurate regression equation. This study’s estimations are useful for determining the values for missing historical weather data, but did not allow the prediction of future values.

Diab and Saade (1999) used a fuzzy inference system with rules developed based on their own intuition about the correlation of weather variables to predict dewpoint temperature for exactly 24 h ahead. The inference rules used the season of the year, barometric pressure, air temperature, and wind speed as inputs, each with their own fuzzy membership functions while the output dewpoint temperature membership functions were expressed as low, medium, and high. The evaluation with 40 uniformly distributed days for all four seasons in 1994 resulted in absolute errors ranging to a maximum of 8°C with no mean error presented.

An artificial neural network (ANN) is a robust computational technique modeled after biological neuron connections found in human brains (Bose and Liang 1995; Haykin 1999). Like the human brain, ANNs are repeatedly exposed to inputs and vary the strength of the connections between neurons based on those inputs. Thus learning for most ANNs is accomplished using an iterative process instead of single calculation as would be used with most types of regression and Bayesian classification. ANNs have been used to help solve many real-world problems such as pattern matching, classification, and prediction (Bose and Liang 1995; Gardner and Dorling 1998; Haykin 1999).

Often ANNs have been used in the atmospheric sciences. Gardner and Dorling (1998) review ANNs used for prediction of ozone concentration and daily maximum ozone, sulfur dioxide concentration, tornadoes, thunderstorms, solar radiation, carbon dioxide, pollutants and monsoon rainfall. More recently, Bodri and Cermak (2000) developed an ANN using 38 yr of rainfall data to predict monthly and yearly precipitation levels for multiple sites in the Czech Republic. Using spatial and temporal data of recent rainfall, Luk et al. (2000) developed an ANN for short-term precipitation prediction focused on predicting flash flood rainfall amounts for 15 min ahead for various areas of western Sydney, Australia. Maqsood et al. (2004) used an ensemble of ANNs to provide 24-h predictions for air temperature, wind speed, and humidity at the Regina Airport in Canada. Wedge et al. (2005) developed an ANN for prediction of waves spilling over sea walls in using sea conditions and wall properties as inputs. Steidley et al. (2005) use ANNs to predict tidal water levels for periods of 3–48 h ahead for a shallow embayment on the coast of Texas in the United States.

Jain et al. (2003, 2006) developed ANNs to predict hourly air temperatures for 1–12 h for three locations in Georgia, United States, using inputs of current air temperature, relative humidity, solar radiation, and wind speed, and up to 6 h of prior data. The MAEs for each location varied from 0.6° to 0.7°C for the 1-h lead time and from 2.4° to 3.0°C for the 12-h lead time. Smith et al. (2006) improved on the results of Jain et al. (2003, 2006) by using cyclic variables to represent the day of year and time of day as additional inputs to the ANN. Smith et al. (2006) also trained multiple ANNs with the same parameters but different initial weights and found that the minimum error on multiple networks provided an improved comparison during model development, with an MAE of 0.54°C for a 1-h prediction and 2.33°C for a 12-h prediction for the evaluation dataset.

Mittal and Zhang (2003) developed ANNs to estimate several weather variables using other weather variables, a process used for estimating missing historical data. Their ANN estimations provided an alternative to the traditional estimations done with psychrometric charts and mathematical models. They developed an ANN model to estimate wet-bulb temperature, enthalpy, humidity ratio, specific volume, and dewpoint temperature using dry-bulb temperature and relative humidity as inputs. Their dataset included values obtained from the psychrometric charts that did not correspond to actual historical data or specific locations, but rather to known relationships among weather variables. The MAE for the dewpoint temperature estimation was 0.305°C.

Dewpoint temperature has been estimated (Kimball et al. 1997; Mahmood and Hubbard 2005; Mittal and Zhang 2003; Parlange and Katz 2000) and analyzed for long-term trends (Robinson 1998, 2000; Sandstrom et al. 2004), but there is little research on short-term dewpoint temperature prediction. The overall goal of the research presented herein was to develop ANN models for predicting hourly dewpoint temperatures for up to 12 h in advance. Specific objectives were to identify the important weather-related inputs that affect dewpoint temperature prediction, to determine the preferred values of the ANN parameters, and to determine the preferred duration of prior data for each lead time. The application of the resulting models would be to predict short-term hourly dewpoint temperature for any location in Georgia.

2. Methodology

a. Data

The University of Georgia Automated Environmental Monitoring Network (AEMN) provides Web-based delivery of current and historical weather data, as well as weather-based tools and applications useful for decision making in agricultural production and natural resource management (additional information is available online at http://www.georgiaweather.net; Hoogenboom 2000). With over 70 weather stations distributed throughout Georgia, each station measures weather data for variables including air temperature, relative humidity, vapor pressure, wind speed and wind direction, solar radiation, atmospheric pressure, and rainfall. Vapor pressure deficit and dewpoint temperature are calculated based from these variables using standard methods. The total amount of rainfall and average of every other variable is determined for each 15-min interval based on 1-s observations. Although the AEMN data collection began for some locations in 1992, the determination of dewpoint temperature only started in September 2002 following requests from the horticultural industry.

Data from 40 of the AEMN weather stations were used in this study: 20 sites were used for model development, and 20 different sites were used for model evaluation. These sites were selected to represent the geographic and regional diversity of Georgia as shown in Fig. 1. The years 2002–04 were used for model development, and the year 2005 was reserved for final evaluation of the model.

Fig. 1.

AEMN weather stations; 20 sites were selected for model development and 20 sites were selected for model evaluation.

Fig. 1.

AEMN weather stations; 20 sites were selected for model development and 20 sites were selected for model evaluation.

The initial weather-related inputs considered included current and prior values of air temperature, relative humidity, vapor pressure, vapor pressure deficit, wind speed, solar radiation, rainfall, and dewpoint temperature. A sequence of prior values through the current value constitutes a history of that variable and is referred to as prior data. For each of the weather-related variables, an hourly rate of change was calculated for prior points in time and used as an additional input. For example, the rate of change for dewpoint temperature between two and three hours prior to the time of prediction t is Td(t−2)Td(t−3). Smith et al. (2006) found that including the rate of change of weather-related input variables reduced the MAE for air temperature prediction. Both time of day and day of year were included as inputs and encoded, because of the cyclic nature of days and years, using four cyclical variables with fuzzy logic–type membership functions. An example of the fuzzy logic–type membership function used for time of day is shown in Fig. 2. If the time of day is 1200 h local time, then the fuzzy logic membership functions shows 1.0 as the degree to which it is noon, and the degree to which it is the other three as 0.0. If the time of day is 0900, the fuzzy logic membership function shows the degree to which it is noon and morning as 0.5, and the degree to which it is evening and midnight as 0.0. If the time of day is an intermediate value, the fuzzy membership function gives a scaled value indicating how much that time of day is represented by the adjacent cyclic categories. Four similar fuzzy membership functions for seasons were used to represent the day of year.

Fig. 2.

The degree of membership for four cyclic input variables for time of day as determined by the fuzzy membership functions. Four cyclic input variables for day of year were determined by similar fuzzy membership functions.

Fig. 2.

The degree of membership for four cyclic input variables for time of day as determined by the fuzzy membership functions. Four cyclic input variables for day of year were determined by similar fuzzy membership functions.

b. Artificial neural network model

A separate ANN model incorporating the error backpropagation (EBP) algorithm was developed for each lead time. The EBP ANN consists of artificial neurons, called nodes, arranged into three layers: input, hidden, and output. The input layer receives the data one case at a time; one or more hidden layers connect the input and output layers and the output layer is interpreted as the prediction, classification, or pattern. Each node at each layer is connected to some (i.e., partially connected) or all (i.e., fully connected) of the nodes in the next layer and each connection has a weight which changes the value going through that connection. The nodes in the hidden layer and output layer can receive inputs from several nodes. These inputs are summed and then presented to an activation function. When the ANN is learning a single training pattern, the pattern values feed forward through the network to produce an output. An error is calculated as the difference between the ANN output and the observed value associated with that input. The partial derivatives of that error are used to adjust the weights using a gradient descent [for a complete description see Haykin (1999)].

The ANN used in this research had a Ward architecture with three fully connected layers: input, hidden, and output. This architecture has three slabs of nodes in the single hidden layer with the nodes in each slab using a different activation function (Ward System Group 1993). Neuroshell 2, the original Ward architecture ANN program, did not have the capacity for the number of observations in the dataset, so an ANN program with the Ward architecture was developed. The Ward architecture has been used for air temperature prediction (Jain et al. 2003, 2006; Smith et al. 2006) and dewpoint temperature estimation (Mittal and Zhang 2003). Each of the three slabs had the same number of nodes and used the Gaussian, Gaussian complement, and hyperbolic tangent activation functions as shown in Fig. 3. The number of nodes in each slab of the hidden layer and number of input nodes were varied during model development. The output layer always consisted of a single node using a logistic activation function, and it represented the predicted dewpoint temperature (°C). Twelve separate models were developed to predict hourly dewpoint temperatures for lead times of 1–12 h. The input layer was scaled to a range of 0.1–0.9 based on the extreme values for each input in the development dataset. These settings were based on previous work by Jain et al. (2003) and Smith et al. (2006), who showed that this type of ANN was suitable for air temperature prediction.

Fig. 3.

Ward EBP ANN architecture with a single hidden layer consisting of three slabs of hidden nodes with different activation functions: Gaussian, Gaussian complement, and hyperbolic tangent.

Fig. 3.

Ward EBP ANN architecture with a single hidden layer consisting of three slabs of hidden nodes with different activation functions: Gaussian, Gaussian complement, and hyperbolic tangent.

An EBP ANN model has two modes. The first is a feed-forward mode where a set of inputs xi, where i ranges from 1 to I, is mapped to a single output z by the following equations:

 
formula
 
formula

where αji are the weights from the input layer to the hidden layer, βj are the weights from the hidden layer to the output node, and yj is the output of the nodes in the hidden layer, where j ranged from 1 to J. The logistic activation function g is defined as follows:

 
formula

where n is the input to the activation function. The hyperbolic tangent, Gaussian, and Gaussian complement are the respective components of the hidden layer activation function f, defined as follows:

 
formula

where n is the input to the activation function.

The second mode of the ANN is backpropagating the error to adjust the weights. The weight adjustment Δ(βj) for each weight from the hidden layer to the output node βj is defined as

 
formula

and the weight adjustment Δ(αji) for each weight from the input layer to the hidden layer αji is defined as

 
formula

where η is the learning rate and t is the target output value. The nodes y0 and x0 are bias nodes that are always set to 1, although their corresponding weights, β0 and αj0, are adjusted. The adjustments for all the weights were applied after each training pattern and this is referred to as a learning event. An EBP ANN with all the parameters including inputs, initial weight range, number of hidden nodes per slab, and learning rate is referred to herein as a model. A single instantiation of the model with random initial weights and a randomly ordered set of training observations selected from the development dataset is referred to as a network.

Traditionally, EBP ANNs use observations in a training dataset to search iteratively for an optimal set of weights that connect the nodes between adjacent layers. A separate testing dataset is used to stop the training when the testing dataset error reaches a minimum. A separate selection dataset is used as a dataset to judge the error of that network after training has been stopped and a comparison of selection dataset errors is used for selection of parameters during model development. Preliminary tests indicated that a testing dataset was not necessary if the training dataset was sufficiently large. The mean absolute error of the training and testing datasets, though slightly different, always tracked each other with as few as 20 000 independent observations in each dataset (e.g., as the training dataset error continued to decrease, the testing dataset error did as well).

Overtraining, where the ANN is able to make accurate predictions on the training dataset, but not on the testing and selection datasets can be a problem for ANNs. These preliminary tests indicated overtraining was not a concern as the error continued to decrease on both training and testing datasets even after 5 000 000 learning events when the training and testing datasets consisted of at least 100 000 observations. This held true for networks with a single or multiple weather-related inputs. It was, therefore, decided that a testing dataset would not be used and a fixed number of learning events would be used to stop training. An epoch is one pass through all the observations in the training dataset. With 100 000 observations in the training dataset the decrease in the mean absolute error from epoch 9 to 10 was typically less than 0.01°C and always less than 0.06°C, so the stopping criteria for training was arbitrarily fixed at 10 epochs of 100 000 observations each, that is, 1 000 000 learning events. For model development, the selection dataset errors were compared in order to select values of ANN parameters for determining the most accurate model.

All model development was conducted using data from the development dataset, which consisted of approximately 1 560 000 observations. Because the development data spanned less than three years, it was not partitioned into separate years for the training and selection datasets. To obtain the best representative sample the training and selection datasets consisted of 100 000 observations randomly selected without replacement from the development dataset for each network. The training and selection datasets were independent, and each represented 20 cities for three years of data from 2002 to 2004.

c. Measurement of model error

The MAE between predicted and observed dewpoint temperature for a particular dataset was selected as the measure of accuracy. For model development this was the selection dataset, and for model evaluation this was the evaluation dataset. Because each network was instantiated with random weights and the training and selection datasets were selected and ordered randomly, networks representing the same model produced different MAEs. Thirty observations were considered as an adequate population sample to closely approximate statistical measurements such as the mean for the population (Freund and Wilson 1993). Therefore, it was arbitrarily decided that 30 networks, referred to as a network set, would be used to determine the accuracy of a model during model development. The population then would be all instances of a model, and each network would be one sampling. As with any distribution, the more samples the higher the statistical validity, but computational time was also a consideration. One network trained for 1 000 000 learning events required 1–6 h of computational time depending on the parameters, making 30 networks require 30–180 h of computational time. Once trained, a network evaluated in feed-forward mode on 100 000 observations required only several minutes. All tests were conducted on 36 personal computers, that is, 32 Pentium 4 and 4 Pentium 3 computers, in the computer laboratories of the Department of Biological and Agricultural Engineering at the University of Georgia.

Because of the nonnormal distribution of the errors for a network set, a number of different statistical measurements were considered to approximate the error of a model based on a network set. A preliminary test considered seven statistical measurements. Four statistical measurements of central tendency were considered: the mean, the mean truncated 20%, the mean truncated 40%, and the median. A truncated or trimmed mean is the mean of the remaining values after a percentage is removed, half from the minimums and half from the maximums. The truncated mean is useful as a robust measure of central tendency, especially for asymmetric distributions (Marazzi and Ruffieux 1999). Three minima were considered: the minimum, the average of the minimum 5, and the average of the minimum 10. Of all seven statistical measures, the average of the minimum five provided the smallest range and standard deviation among the 30 network set instantiations for the preliminary test, suggesting this statistical measure may be more stable than the minimum which had been used in ANN temperature prediction research (Jain et al. 2003; Smith et al. 2006). Therefore, the average of the minimum five MAEs for a network set was used to approximate the error of a model and was referred to as the MAE for that model during model development.

d. Experimental procedure

In the first experiment, the preferred set of weather-related inputs was determined using a 6-h lead time and an 18-h duration of prior data. Dewpoint temperature, air temperature, relative humidity, vapor pressure, vapor pressure deficit, wind speed, solar radiation, and rainfall were the inputs considered in this search. Dewpoint temperature was selected as the first weather-related input considered, and the remaining predictors were selected in an iterative fashion: ANN models using dewpoint temperature paired with each of the remaining weather-related inputs were compared, and the input that produced the lowest error was retained. The two weather-related inputs were then combined with each of the remaining inputs to form models with three weather-related inputs, and the one with the lowest error was retained. This process was continued until all the possible inputs were included or models with additional inputs did not produce a smaller error than the previous preferred model. The initial ANN parameters were arbitrarily chosen to be 20 hidden nodes per slab for a total of 60 nodes in the hidden layer, a learning rate of 0.1, and an initial weight of ±0.2.

In the second experiment, the preferred values for the following ANN parameters were determined: number of hidden nodes per slab, initial weight range, and learning rate. As each parameter was varied the current preferred model was determined by the model with the minimum error. This experiment used the previously determined weather-related inputs and a 6-h lead time.

In the third experiment the preferred duration of prior data was determined for each lead time and varied between 1 and 12 h. Preliminary tests indicated that the duration of prior data was correlated to the lead time and a search for the preferred model for all lead times should range from 6 to 30 h. To help ensure the reliability of the preferred model for each lead time, two models with longer durations of prior data and two models with shorter durations of prior data were also developed.

The training for the final evaluation was conducted by training 30 networks for each of the 12 lead times using half of the development dataset (i.e., approximately 780 000 observations) for a training dataset instead of the 100 000 observations used during model development. The other half was used as a selection dataset to choose the preferred network for each lead time model. The 12 preferred networks, which represented the 12 final models, were used in feed-forward mode for model evaluation on the evaluation dataset. The predictions of the 12 final models were directly compared with predictions using the current dewpoint temperature as the predicted value.

3. Model development

As stated in the previous section during the search for the important weather-related inputs, several values were held constant including 20 hidden nodes per slab, an 18-h duration of prior data, a 0.1 learning rate, a 0.2 initial weight range and a lead time of 6 h. The fuzzy membership function inputs for time of day and day of year (Fig. 2) were also included in each model that was developed. When dewpoint temperature was considered as the only weather-related input, the MAE was 1.620°C (Table 1). The dewpoint temperature–only model was then coupled with each possible remaining weather-related input to determine the best two-weather-variable ANN. The model with dewpoint temperature and relative humidity produced the lowest MAE of 1.521°C. Continuing with this approach, the weather-related inputs in order of importance with respect to weather variables 3–6 were solar radiation, air temperature, wind speed, and vapor pressure. The ANN with six weather-related inputs resulted in the lowest MAE, 1.463°C (Table 1). Vapor pressure deficit and amount of rain did not improve model accuracy when they were included.

Table 1.

The effect of selected weather-related input combinations on dewpoint temperature prediction for the development dataset using artificial neural networks.

The effect of selected weather-related input combinations on dewpoint temperature prediction for the development dataset using artificial neural networks.
The effect of selected weather-related input combinations on dewpoint temperature prediction for the development dataset using artificial neural networks.

For the second of the experiments described in section 2d, the number of hidden nodes per slab was varied from 10 to 70 in increments of 10. The MAE decreased from 1.471°C to 1.463°C when the number of hidden nodes was increased from 10 to 20 nodes per slab, but thereafter increasing the number of nodes per slab had a negligible effect on accuracy. Therefore, the number of hidden nodes per slab selected was 20.

The range of initial weights was varied from ±0.05 to ±0.40 in increments of 0.05. An initial weight range of ±0.15 resulted in the lowest MAE of 1.463°C and was therefore selected for further model development. The learning rate was varied from 0.05 to 0.60 in increments of 0.05. A model with a learning rate of 0.35 had the lowest MAE, 1.445°C, and was selected for further model development.

For the third of the experiments described in section 2d, the duration of prior data was varied from 6 to 30 h in increments of 6 h for the 12 lead times, and in some cases the range of the duration was extended (Table 2). The model with the lowest MAE and, in the case of a tie, the lowest coefficient of variation (CV) for the MAE, for each lead time was selected as the best model for model development. The best models for the 1- and 2-h lead times were the models that included 6 h of prior data. The best models for the 5-, 6-, 7-, 9-, and 12-h lead times included 18 h of prior data. The best models for the 3-, 4-, 10-, and 11-h lead times included 24 h of prior data. The best model for the 8-h lead time included 30 h of prior data. Therefore, these values did not show a clear relationship between duration of prior data and lead time.

Table 2.

The effect of the duration of prior data and lead time on dewpoint temperature prediction based on the MAE* and its CV.

The effect of the duration of prior data and lead time on dewpoint temperature prediction based on the MAE* and its CV.
The effect of the duration of prior data and lead time on dewpoint temperature prediction based on the MAE* and its CV.

4. Results and discussion

The final results for model evaluation are for the single best network from the chosen model (Fig. 4). The MAEs for the 1-, 4-, 8-, and 12-h prediction models were 0.550°C, 1.234°C, 1.799°C, and 2.281°C, respectively, with a coefficient of determination (r2) of 0.993, 0.964, 0.924, and 0.889, respectively. As expected the MAE values increased and the r2 values decreased as the lead time increased. There was also a tendency to overpredict at low dewpoint temperatures.

Fig. 4.

Performance of predicted dewpoint temperature for the evaluation dataset for the (a) 1-, (b) 4-, (c) 8-, and (d) 12-h prediction models.

Fig. 4.

Performance of predicted dewpoint temperature for the evaluation dataset for the (a) 1-, (b) 4-, (c) 8-, and (d) 12-h prediction models.

A comparison was conducted for the final results for model evaluation with predictions using the current dewpoint temperature as the predicted temperature for the same observations (Table 3). The improvement of the ANN model over the current dewpoint temperature was 0.035°C for the 1-h model, 0.162°C for the 2-h model, 0.212°C for the 3-h model, and varied between 0.3°C and 0.4°C for the 4–12-h models. The percent improvement for the 2–10-h models was relatively similar, ranging from 15.5% to 21.4%, but differed at the lower end, where the 1-h model improved by only 6.0%, and at the higher end where the 11-h model improvement was 14.7% and the 12-h model improvement was 11.9%. The poorer prediction ability for the lower- and higher-hour models suggests that development of the preferred ANN models for those lead times might require searching for the optimal model parameters for those lead times separately. The development of these models included an iterative search for the preferred duration of prior data for each lead time, but did not include the search for preferred weather-related inputs and the ANN model parameters for each lead time. Because those searches were only conducted for the 6-h lead time, the models may be biased in favor of 6-h predictions and not generalize as well to the lower and higher lead times. A full comparison with other methods of dewpoint temperature prediction was outside the scope of this paper, but would be an appropriate follow-up study to understand how ANN predictions compare to other intelligent methods, such as advanced regression models and Bayesian learning, and how other intelligent methods compare to physical weather models.

Table 3.

Comparison of the MAEs of using the current dewpoint temperature as the predicted dewpoint temperature and using the final ANN model for the evaluation dataset for lead times of 1–12 h.

Comparison of the MAEs of using the current dewpoint temperature as the predicted dewpoint temperature and using the final ANN model for the evaluation dataset for lead times of 1–12 h.
Comparison of the MAEs of using the current dewpoint temperature as the predicted dewpoint temperature and using the final ANN model for the evaluation dataset for lead times of 1–12 h.

Sample periods were selected that included the extremes of low and high air temperature conditions to demonstrate the prediction of dewpoint temperature for these situations. A sample period from 18 to 20 March 2005, for Dahlonega, Georgia, was selected as an example of two early morning freezes in late winter. This scenario would represent a situation in which a fruit crop could experience catastrophic damage from frost during the blooming phase of the crop. The predictions of dewpoint temperature for the 1-, 4-, 8-, and 12-h models indicated more accurate predictions for the shorter than the longer lead times during these winter freezes (Fig. 5). The 1- and 4-h predictions showed a drop in dewpoint temperature during the freeze event, but the 4-h model placed it later than it actually occurred. In contrast, the 8- and 12-h models did not predict the drop in dewpoint temperature, but instead predicted that it would remain steady around 1°–3°C. Similarly, the low dewpoint temperature between 1200 and 1800 h on 19 March was predicted well by the 1-h prediction, fairly accurately with the 4-h model predicting an even lower dewpoint temperature, and less accurately by the 8- and 12-h models that predicted higher values for the dewpoint temperature than actually occurred.

Fig. 5.

Predicted dewpoint temperature for freezing conditions for Dahlonega, GA, with (a) 1-, (b) 4-, (c) 8-, and (d) 12-h prediction models in March 2005. Observed dewpoint temperature and air temperature are also shown.

Fig. 5.

Predicted dewpoint temperature for freezing conditions for Dahlonega, GA, with (a) 1-, (b) 4-, (c) 8-, and (d) 12-h prediction models in March 2005. Observed dewpoint temperature and air temperature are also shown.

For the prediction of a high dewpoint temperature associated with an extreme of high air temperature, a sample period from 22 to 23 August 2005, for Statesboro, Georgia, was selected. The highest observed dewpoint temperature in Statesboro during 2005 occurred on 22 August. The predictions of dewpoint temperature for the 1-, 4-, 8-, and 12-h models again indicated more accurate predictions for shorter lead times compared to longer lead times for this extreme event during summertime (Fig. 6). The 1-, 4-, and 8-h models predicted the dewpoint temperature accurately from 1200 to 1800 h, the highest air temperature portion of 22 August, where the 12-h model prediction did not vary during that time as the observed dewpoint temperature changed. All models were less accurate for the high dewpoint temperature that occurred between 1800 and 2100 h on 22 August. Only the 1-h model predicted the climbing dewpoint temperature during this period, yet it did not accurately predict the maximum value. The 4-, 8-, and 12-h models predicted a relatively stable dewpoint temperature for this period.

Fig. 6.

Predicted dewpoint temperature for extreme heat condition for Statesboro, GA, with (a) 1-, (b) 4-, (c) 8-, and (d) 12-h prediction models in August 2005. Observed dewpoint temperature and air temperature are also shown.

Fig. 6.

Predicted dewpoint temperature for extreme heat condition for Statesboro, GA, with (a) 1-, (b) 4-, (c) 8-, and (d) 12-h prediction models in August 2005. Observed dewpoint temperature and air temperature are also shown.

The 12 ANN models can be sequenced in order to provide a 12-h prediction track for dewpoint temperature. This is illustrated in Fig. 7 using an early morning freeze example from 14 to 15 March 2005, for Tiger, Georgia. The 2100-h prediction track shows a slight decrease in the dewpoint temperature, but it overpredicted the dewpoint temperature during the freeze by 4°–5°C. Yet predicting only three hours later at midnight, the prediction track more closely followed the actual freeze that occurred. It also indicated that the dewpoint temperature would remain slightly above 0°C until 0400–0500 h, while the observed dewpoint temperature fell below 0°C around 0200 h. Even with that inaccuracy, the midnight prediction track in comparison with the 2100-h prediction track is extremely accurate and correctly shows that the dewpoint temperature would decrease to below 0°C, that the minimum dewpoint temperature would occur between 0600 and 0700 h, and that the dewpoint temperature would increase from 0700 to 1200 h.

Fig. 7.

Predicted dewpoint temperature at 2100 and 2400 h on 14–15 Mar 2005 for Tiger, GA, based on a sequence of 12 models. The observed dewpoint temperature and air temperature for this period are also shown.

Fig. 7.

Predicted dewpoint temperature at 2100 and 2400 h on 14–15 Mar 2005 for Tiger, GA, based on a sequence of 12 models. The observed dewpoint temperature and air temperature for this period are also shown.

The models developed in this research show how dewpoint temperature can be predicted for a short time period with an ANN. Although the results varied, the ANN models were able to predict dewpoint temperature adequately for many difficult conditions, including during extreme heat and freezing conditions. These types of predictions are useful in decision making for ecologists, meteorologists, agricultural producers, and others who work with real-time weather data.

5. Application and future work

As shown, the 12 ANN models can be used in sequence to represent a continuous dewpoint temperature prediction from the prediction time to 12 h ahead. Although these models can predict for any location in Georgia, prediction beyond Georgia could be problematic as the models have not been trained with data from weather conditions specific to those locations. These types of prediction tracks have been implemented as part of a decision support system on the AEMN Web site (www.georgiaweather.net), a weather-based information system. For future research, possible experiments could include examining different criteria for stopping training and examining the use of momentum in combination with various learning rates to produce the optimal results. Another possibility would be expanding the region to make models for the entire southern or contiguous United States. Because dewpoint temperature varies dramatically with season, another approach would be to train four ANNs, one for each season. The four seasonal ANNs could be used individually or they could be combined with an ensemble ANN approach.

Acknowledgments

This work was funded in part by a partnership between the USDA-Federal Crop Insurance Corporation through the Risk Management Agency and the University of Georgia and by state and federal funds allocated to Georgia Agricultural Experiment Stations Hatch projects GEO00877 and GEO01654.

REFERENCES

REFERENCES
Agam
,
N.
, and
P. R.
Berliner
,
2006
:
Dew formation and water vapor absorption in semi-arid environments—A review.
J. Arid Environ.
,
65
,
572
590
.
Bodri
,
L.
, and
V.
Cermak
,
2000
:
Prediction of extreme precipitation using a neural network: Application to summer flood occurrence in Moravia.
Adv. Eng. Software
,
31
,
311
321
.
Bose
,
N. K.
, and
P.
Liang
,
1995
:
Neural Network Fundamentals with Graphs, Algorithms, and Applications.
McGraw-Hill, 512 pp
.
Diab
,
H. B.
, and
J. J.
Saade
,
1999
:
Weather prediction using fuzzy sets and inference methodology.
J. Intell. Fuzzy Syst.
,
7
,
283
305
.
Freund
,
R. J.
, and
W. J.
Wilson
,
1993
:
Statistical Methods.
Academic Press, 624 pp
.
Gardner
,
M. W.
, and
S. R.
Dorling
,
1998
:
Artificial neural networks (the multilayer perceptron)—A review of applications in the atmospheric sciences.
Atmos. Environ.
,
32
,
2627
2636
.
Haykin
,
S.
,
1999
:
Neural Networks: A Comprehensive Foundation.
2nd ed. Prentice Hall, 696 pp
.
Hoogenboom
,
G.
,
2000
:
The Georgia automated environmental monitoring network. Preprints, 24th Conf. on Agricultural and Forest Meteorology, Davis, CA, Amer. Meteor. Soc., 24–25
.
Hubbard
,
K. G.
,
R.
Mahmood
, and
C.
Carlson
,
2003
:
Estimating daily dew point temperature for the northern Great Plains using maximum and minimum temperature.
Agron. J.
,
95
,
323
328
.
Jain
,
A.
,
R. W.
McClendon
,
G.
Hoogenboom
, and
R.
Ramyaa
,
2003
:
Prediction of frost for fruit protection using artificial neural networks. American Society of Agricultural Engineers., St. Joseph, MI, ASAE Paper 03-3075
.
Jain
,
A.
,
R. W.
McClendon
, and
G.
Hoogenboom
,
2006
:
Freeze prediction for specific locations using artificial neural networks.
Trans. ASABE
,
49
,
1955
1962
.
Kimball
,
J. S.
,
S. W.
Running
, and
R.
Nemani
,
1997
:
An improved method for estimating surface humidity from daily minimum temperature.
Agric. For. Meteor.
,
85
,
87
98
.
Luk
,
K. C.
,
J. E.
Ball
, and
A.
Sharma
,
2000
:
A study of optimal model lag and spatial inputs for artificial neural network for rainfall forecasting.
J. Hydrol.
,
227
,
56
65
.
Mahmood
,
R.
, and
K. G.
Hubbard
,
2005
:
Assessing bias in evapotranspiration and soil moisture estimates due to the use of modeled solar radiation and dew point temperature data.
Agric. For. Meteor.
,
130
,
71
84
.
Maqsood
,
I.
,
M. R.
Khan
, and
A.
Abraham
,
2004
:
An ensemble of neural networks for weather forecasting.
Neural Comput. Appl.
,
13
,
112
122
.
Marazzi
,
A.
, and
C.
Ruffieux
,
1999
:
A truncated mean as an asymmetric distribution.
Comput. Stat. Data Anal.
,
32
,
79
100
.
Merva
,
G. E.
,
1975
:
Physioengineering Principles.
Avi, 353 pp
.
Mittal
,
G. S.
, and
J.
Zhang
,
2003
:
Artificial neural network-based psychrometric predictor.
Biosyst. Eng.
,
85
,
283
289
.
Parlange
,
M. B.
, and
R. W.
Katz
,
2000
:
An extended version of the Richardson model for simulating daily weather variables.
J. Appl. Meteor.
,
39
,
610
622
.
Robinson
,
P. J.
,
1998
:
Monthly variations of dew point temperature in the coterminous United States.
Int. J. Climate
,
18
,
1539
1556
.
Robinson
,
P. J.
,
2000
:
Temporal trends in United States dew point temperatures.
Int. J. Climate
,
20
,
985
1002
.
Sandstrom
,
M. A.
,
R. G.
Lauritsen
, and
D.
Changnon
,
2004
:
A central-U.S. summer extreme dew-point climatology (1949-2000).
Phys. Geogr.
,
25
,
191
207
.
Smith
,
B. A.
,
R. W.
McClendon
, and
G.
Hoogenboom
,
2006
:
Improving air temperature prediction with artificial neural networks.
Int. J. Comput. Intell.
,
3
,
179
186
.
Snyder
,
R. L.
, and
J. P.
de Melo-Abreu
,
2005
:
Frost Protection: Fundamentals, Practice and Economics.
Vol. 1. Food and Agriculture Organization of the United Nations, 223 pp
.
Steidley
,
C.
,
A.
Sadovski
,
P.
Tissot
, and
R.
Bachnak
,
2005
:
Using an artificial neural network to improve predictions of water level where tide charts fail.
Innovations in Applied Artificial Intelligence, M. Ali and F. Esposito, Eds., Springer, 599–608
.
Ward System Group
,
1993
:
Manual of NeuroShell 2. Ward System Group
.
Wedge
,
D.
,
D.
Ingram
,
D.
McLean
,
C.
Mingham
, and
Z.
Bandar
,
2005
:
A global-local artificial neural network with application to wave overtopping prediction.
Artificial Neural Networks: Formal Models and Their Applications–ICANN 2005, Springer, 109–114
.

Footnotes

Corresponding author address: G. Hoogenboom, Department of Biological and Agricultural Engineering, University of Georgia, Griffin, GA 30223. Email: gerrit@uga.edu