**7. Other ANN studies**

The comparative data we have shown for specific locations, and also the isohyet for the subregion, indicate that ANNs can give more skillful forecasts than the general circulation models currently relied upon by the Australian Bureau of Meteorology.

We have also published a series of articles describing the application of ANNs to monthly rainfall forecasting in other parts of Australia including northern and central Queensland [11–13, 15–17] the Murray Darling Basin [14] and Western Australia [19]. The forecasts for these regions also use a combination of large-scale climate indices and the local variables temperature and rainfall with lead times between 1 and 18 months.

The island state of Tasmania lies to the south of mainland Australia, and has an area similar to that of the region of south-eastern Queensland considered above. Tasmania is primarily reliant on hydro-electric power, and therefore the state is highly dependent on rainfall for electricity generation. Until 2005, Tasmania was self-reliant for electricity when the Basslink interconnector to mainland Victoria was completed. This link was intended to both provide energy security, in case of drought; and provide renewable energy to Victoria, which relies heavily on coal for power generation. Hydro Tasmania water storage levels decreased from over 60% capacity in 2013 to below 15% in early 2016. The state experienced an energy crisis in 2016 following 2 years of high volumes of energy export to Victoria, followed by low rainfall and a fault in the link to the mainland.

This situation emphasized the need to incorporate more accurate rainfall forecasts in planning decisions relating to hydro-electricity generation. The skill of monthly forecasts for this region of Australia at 2–3 months lead time generated by the Australian Bureau of Meteorology for this region are in the range −10 to 10%, averaging close to climatology [39]. Tasmania has at least 30 sites with long rainfall records extending back about a century or longer, distributed over the island. It should therefore be possible to construct regional or catchment forecasts for medium-term rainfall. One example is shown for Hobart, the capital of Tasmania in **Figure 8**. This shows forecasts of monthly rainfall at a 3 month lead time for a test period of

10 years from January 2004 to December 2013. **Table 5** gives the corresponding skill scores for each month, which lie in the range 34–71%. This is significant improvement on that currently

**Table 5.** Forecast skill as a percentage for monthly rainfall forecasts for Hobart with reference to climatology for the

achievable using general circulation models.

composite ANN model and POAMA.

Rainfall (mm)

1

7

13

19

25

31

37

43

**Figure 8.** Observed (blue) and forecast (red) monthly rainfall for Hobart, Tasmania with a lead time of 3 months.

49

55

61

Month in test period

67

73

79

Forecasting of Medium-term Rainfall Using Artificial Neural Networks: Case Studies…

85

91

97

103

109

115

http://dx.doi.org/10.5772/intechopen.72619

47

Forecasting of Medium-term Rainfall Using Artificial Neural Networks: Case Studies… http://dx.doi.org/10.5772/intechopen.72619 47

skill score worse than climatology. **Table 4** shows skill scores for each individual month using an ANN with a lead time of 12 months and POAMA with a lead time of 8 months. In all cases the ANN skill scores are positive and lie in the range 23–69%. In contrast, the skills cores for

Hawthorne et al. [39] used the output from POAMA to produce monthly rainfall forecasts with up to 8 months lead time for 250 km × 250 km grid areas over continental Australia. The skill of their monthly rainfall forecasts was described as being generally low. Skill scores fell between −20% and 20%, including grid locations in coastal south-east Queensland. For lead times between 3, 4, 5, 6, 7 and 8 months, with approximately 60% of the forecasts give skill levels relative to climatology below 0%. For southeast Queensland only about 20% of the forecasts had a skill level in the 15–20% range [39] Hawthorne et al. [39] described the skill of their monthly rainfall forecasts as low, and concluded that monthly rainfall forecasting with

The comparative data we have shown for specific locations, and also the isohyet for the subregion, indicate that ANNs can give more skillful forecasts than the general circulation mod-

We have also published a series of articles describing the application of ANNs to monthly rainfall forecasting in other parts of Australia including northern and central Queensland [11–13, 15–17] the Murray Darling Basin [14] and Western Australia [19]. The forecasts for these regions also use a combination of large-scale climate indices and the local variables

The island state of Tasmania lies to the south of mainland Australia, and has an area similar to that of the region of south-eastern Queensland considered above. Tasmania is primarily reliant on hydro-electric power, and therefore the state is highly dependent on rainfall for electricity generation. Until 2005, Tasmania was self-reliant for electricity when the Basslink interconnector to mainland Victoria was completed. This link was intended to both provide energy security, in case of drought; and provide renewable energy to Victoria, which relies heavily on coal for power generation. Hydro Tasmania water storage levels decreased from over 60% capacity in 2013 to below 15% in early 2016. The state experienced an energy crisis in 2016 following 2 years of high volumes of energy export to Victoria, followed by low rainfall

This situation emphasized the need to incorporate more accurate rainfall forecasts in planning decisions relating to hydro-electricity generation. The skill of monthly forecasts for this region of Australia at 2–3 months lead time generated by the Australian Bureau of Meteorology for this region are in the range −10 to 10%, averaging close to climatology [39]. Tasmania has at least 30 sites with long rainfall records extending back about a century or longer, distributed over the island. It should therefore be possible to construct regional or catchment forecasts for medium-term rainfall. One example is shown for Hobart, the capital of Tasmania in **Figure 8**. This shows forecasts of monthly rainfall at a 3 month lead time for a test period of

POAMA forecasts are negative, that is worse than climatology.

els currently relied upon by the Australian Bureau of Meteorology.

temperature and rainfall with lead times between 1 and 18 months.

POAMA remained a challenge.

46 Engineering and Mathematical Topics in Rainfall

and a fault in the link to the mainland.

**7. Other ANN studies**

**Figure 8.** Observed (blue) and forecast (red) monthly rainfall for Hobart, Tasmania with a lead time of 3 months.


**Table 5.** Forecast skill as a percentage for monthly rainfall forecasts for Hobart with reference to climatology for the composite ANN model and POAMA.

10 years from January 2004 to December 2013. **Table 5** gives the corresponding skill scores for each month, which lie in the range 34–71%. This is significant improvement on that currently achievable using general circulation models.

Other studies, including by Bagirov et al. [40] predicted monthly rainfall for 8 sites in Victoria with 5 input meteorological variables, using data over the period 1889–2014. Montazerolghaem et al. [41] made monthly rainfall forecasts from 136 weather stations in south-eastern Australia in the states of Victoria, NSW, South Australia and southern Queensland with 1 month lead time. Using large scale climate indices, He et al. [42] made forecasts of monthly rainfall at 255 stations across Australia with training data between 1959 and 1889 test data between 1999 and 2008 with large-scale climate indices as inputs.

ANNs have been applied to rainfall forecasting in other parts of the world [25, 26, 43], with **Table 6** showing a survey of 36 articles published between 2014 and 2017 where ANNs have been used to forecast monthly or seasonal rainfall. The majority of these investigations were from Asia, particularly India and China.

ANNs have also been applied to rainfall forecasting at both shorter forecast periods, such as hourly [44] and daily [45] as well as longer forecast periods including annual [46]. ANNs have also been used to forecasting other climatic and meteorological variables including temperatures [47–50] and wind speed [51, 52]. Other machine learning methods have also been applied to rainfall forecasting; including support vector machines (SVM) [53] and adaptive neuro-fuzzy inference systems (ANFIS) [54–56].

ideally suited to such studies. **Country Region Forecast period Reference AUSTRALIA** Australia Queensland and Western Australia Monthly [20] Australia Queensland Monthly [21] Australia Victoria Monthly [40] Australia Bowen Basin, Queensland Monthly [18] Australia Western Australia Monthly [19] Australia south-eastern and eastern Australia Monthly [41] Australia Miles Murray Darling Basin, Monthly [14]

The survey results detailed in **Table 6** indicate that there have been very few studies of ANNs and their application to rainfall forecasting in North America and Europe. These are regions that are likely to have the longest rainfall and temperature series and therefore are potentially


**8. Conclusion**

**NORTH AMERICA**

**MIDDLE EAST**

**AFRICA**

While general circulation models are used by meteorological agencies around the world for rainfall forecasting, they do not generally perform well at forecasting medium-term rainfall, despite substantial efforts to enhance performance over many years [36, 81–83]. These are the same models used by the Intergovernmental Panel on Climate Change (IPCC) to forecast climate change over decades. Though recent studies suggest ANNs have considerable application here, including to evaluate natural versus climate change over millennia, and also to

Iran Mashhad Monthly [76] Iran Qara-Qum catchment Monthly [77] Jordan Arid region Monthly [27]

Ethiopia Upper Blue Nile Basin Seasonal [78] West Africa Sahel region Seasonal [79]

USA California Seasonal [80]

**Country Region Forecast period Reference** China Yellow River Seasonal [60] China Monthly [61] China western Jilin Province, Monthly [62] China Arid region north-west China Monthly [63] India Indian subcontinent monsoon Seasonal [64] India All India monsoon Seasonal [65] India Coonoor region Monthly [66] India Thanjavur district, province of Tamil Nadu Monthly [67] India Andhra Pradesh state Monthly [68] India Assam Monthly [69] India South peninsula Seasonal [70] Malaysia Johor state Monthly [71] Indonesia Ampel, Boyolali Monthly [72] Indonesia Tenggarong Station, East Kalimantan Monthly [73] Thailand Ping Basin Seasonal [74] Thailand North-east region Monthly [75]

Forecasting of Medium-term Rainfall Using Artificial Neural Networks: Case Studies…

http://dx.doi.org/10.5772/intechopen.72619

49

better understand equilibrium climate sensitivity [84].

**Table 6.** Survey of publications on rainfall forecasting 2014-2017.


**Table 6.** Survey of publications on rainfall forecasting 2014-2017.
