An understanding of a species’ activity patterns is important for its conservation. Activity may be adapted according to biotic factors such as resource availability, competition and predation risk, or abiotic factors such as photoperiod and ambient temperature (e.g., [1-3]). For example, more time may be spent in foraging where there is low availability of food resources [4], or activity may be restricted to the coolest times of the day where climates are warmer (e.g., [5]). Any increase in activity with environmental change may incur higher energetic costs and, thus, have an influence on population ecology (e.g., reduced breeding effort, increased mortality rates). Despite its importance, activity patterns are poorly understood for many species due to the limitations of traditional field methodologies.

As a specialist folivore feeding exclusively on Eucalyptus spp., the koala (Phascolarctos cinereus) is particularly susceptible to changes in its environment [6]. The low nutritive value and high fibre content of Eucalyptus foliage, together with the cost of detoxifying secondary plant compounds, interact to limit available energy for the species [7-9]. Consequently, koalas, like many other arboreal herbivores, remain inactive for long periods to conserve energy and aid digestion [10-12]. It is therefore important to understand how koalas apportion time to different behaviors such as feeding and resting, and the factors influencing their activity patterns.

An understanding of koala activity patterns remains a major knowledge gap, with most research to date being undertaken on captive animals [13-18], or in field studies involving limited observations of a few individuals over short time periods (e.g., [11,12,19]). These studies indicate that there is high inter-individual variation in activity due to age, gender and physiological state. In free-ranging populations, factors such as weather, food resources and population density also may influence the activity of individuals, leading to significant variance and lack of analytical power when sample sizes are small. Continuous observation of large numbers of individuals for extended periods, however, is logistically difficult and time-consuming.

Accelerometry is gaining popularity as a tool for indirectly measuring activity in free-ranging animals (e.g., [20-23]). Accelerometer data loggers continuously measure acceleration on up to three axes for an extended period of time. Traditionally used in human studies (e.g., [24-26]), accelerometer data loggers are now being developed for attachment to animals. When attached along an animal’s trunk, multi-axis accelerometer data loggers accurately record its overall body movement [20,23]. For some species, this has provided detailed information on the timing and duration of different activities (e.g., red-footed booby, Sula sula [27]). Furthermore, data from the axes may be combined to derive an estimate of overall dynamic body acceleration (ODBA [23]). Studies suggest that ODBA is highly correlated with energy expenditure in many species [21].

Use of accelerometer data loggers may therefore provide a means of indirectly recording activity in koalas. The aims of this study were to: (1) develop a method for examining activity patterns of koalas, using accelerometry; and (2) apply this method to examining activity of male and female koalas in a high density population of koalas during the breeding season.

There were 16 and 12.5 koalas per hectare in the study area in the early- and late-breeding sampling periods, respectively. In the early-breeding period, 67% of females had back-young, whereas in the late-breeding period, only 25% had back-young present.

Our study has demonstrated that accelerometry is an effective tool for examining activity patterns of an arboreal species. Accelerometer data loggers are small and easily attached to radiocollars and, thus, do not interfere with natural activity of individuals. They provide fine-scale, continuous, multi-day data on animal activity such that large numbers of individuals can be monitored simultaneously. To date, small sample sizes have been typical in studies of animal behavior and, therefore, may not have accounted for high individual variation in behavior [35]. This has been the case with studies of koala activity. For example, one study [11] reported time budgets based on direct observations of four female koalas for 24 hours; and another [19,20] used acoustic devices to monitor activity of five female and six male koalas over 24-h periods. In our study, accelerometers allowed us to examine activity of 27 koalas for 7-d periods, equivalent to a total of 4536 observation hours. We identified a clear diel cycle of activity with most activity occurring during the coolest hours of the day. This pattern did not vary between genders or phase of the breeding season, but overall activity tended to be higher during the early-breeding season.

Accelerometry is gaining popularity as a tool for determining the timing and frequency of specific behaviors in many wildlife species. For example, a pattern in accelerometer traces was identified for walking in cormorants (Phalacrocorax carbo) [23]; and a unique pattern of head movement was associated with prey encounter in penguins (Pygoscelis spp.) [36]. In our study with koalas, we were not able to discern specific accelerometer traces associated with any particular activity that would assist in their identification. Direct observation of koalas suggests that this was due to their relatively erratic movements during all active behaviors. While feeding, koalas alternate between short bursts of high movement (e.g., reaching for leaves, moving to new locations in the tree), and periods of relative inactivity (chewing, observing). Feeding, moving to new roosting points within a tree, and grooming had similar accelerometer traces. Although we are unable to validate this, it may be possible to identify male ‘bellow’ vocalisations as they are associated with a unique, repetitive head movement. Vocalisations play an important role in mate selection and male territoriality (e.g., [37,38]) and, therefore, an ability to determine their duration, timing and frequency would be valuable in understanding aspects of breeding behavior.

Whereas we could not detect specific behaviors from the accelerometer data, we were able to distinguish between inactive and active periods for each individual, based on an index of activity (ODBA) derived from the three accelerometer axes. While sleeping or resting, the index of activity was low (ODBA < 1 g·s^-1) whereas it was up to ten times higher when koalas were feeding, moving or grooming (active behaviors). To define activity bouts, a smoothing filter was applied so that short periods of inactivity (up to 48 s, see Figure 2) within activity bouts were correctly assigned. This allowed us to determine the total amount of time koalas were active per day, and to characterise activity patterns of the study animals, for comparison of the timing and duration of activity bouts between genders and season.

Koalas were active for an average of 5 - 6 h per day which is at the upper end of the range previously reported (3.6 to 5 hours per day [11,14,19,39]). Previous studies that have been based on captive animals, or on limited observation of free-ranging individuals, may have underestimated activity. Captive koalas are held in small enclosures, do not need to search for food, and are housed to prevent aggressive interactions [40]. In studies of free-ranging koalas that exhibit high daily and inter-individual variation in activity, activity estimates based on limited observations may not be representative. Indeed, the high individual variation in total daily activity observed in both sampling periods in our study (4.5 - 7 h·d^-1) highlights the need for large sample sizes in studies of koala activity.

A number of factors may also have contributed to the high levels of koala activity in our study. The study was conducted during the breeding season in an area of extremely high koala population density (>12 koalas per hectare), reflecting abundant availability of high quality food resources (i.e., manna gum [8]). Although koalas moved only short distances (<60 m) within a small area during the 7-d study periods (standard distance of locations <32 m), interactions between individuals were potentially frequent due to the high population density and heightened breeding behavior (e.g., mate defence, copulation attempts). This may have resulted in koalas being active more frequently and for longer periods.

In our study, overall activity (ODBA) was higher during the early- rather than late-breeding season, which is consistent with breeding behaviour in this species. During the early-breeding season, most copulations occur and young are weaned; while in the late-breeding season, there are fewer copulations because most females are either pregnant or have recently given birth. In the early-breeding season, koalas moved farther and were active for slightly longer each day (see Table 3). Furthermore, anecdotal observations suggest that aggressive interactions between males, and copulation attempts were more frequent during this period. The relationship between ODBA and metabolic rate is yet to be validated for koalas; however, studies with other species suggest that ODBA is a reliable proxy for energy expenditure [20,21,23]. It is therefore likely that energy demands for koalas peak during the early-breeding season. Our study also suggests that male and female koalas partition activity differently with males investing more in mate selection and defence. Although the total amount of time spent in activity and ODBA did not vary with gender in either sampling period, males moved farther and changed trees more frequently than females.

The duration of activity bouts was highly variable. The median length of bouts was relatively short (17.5 minutes) and did not vary with gender or season. However, some bouts were as long as 6.4 hours. Previous studies suggest that the majority of koala activity is associated with feeding [19,39,41], but in our study, longer bouts may also have involved movements between trees. Koalas generally moved between trees daily, although this was more frequently observed for males (see Table 3).

We observed a clear pattern of diel activity during both sample periods. Koalas were least active (less than 10 minutes per hour active) from sunrise (06:00 h) to mid-afternoon (14:00 h), after which activity increased to peak between 21:00 - 22:00 h (mean of 25 minutes per hour active; See Figure 3). Koalas are generally considered to be nocturnal, although daytime activity has been reported [11,19,39,41]. It has been suggested that the high levels of daytime activity observed in some studies may be due to study animals having advanced tooth wear causing them to feed for longer periods and to space feeding bouts throughout a 24-h period [19]. In a study where koalas were monitored with acoustic devices, nocturnal activity was reported in koalas with low-to-medium tooth wear, but activity throughout a 24-h period in koalas with advanced tooth wear [19]. Although we did not measure tooth wear as part of this study, other studies of the same population suggest that individuals with advanced tooth wear represent only a small proportion (<5%) of individuals (D. Whisson, unpublished data) such that tooth wear was unlikely to have had any influence on activity in our study.

In both sampling periods, activity was correlated with hourly temperature, with activity increasing with declining ambient temperature. This is consistent with the species’ thermoregulatory properties [42]. Although koalas can endure cold conditions as a result of the insulative properties of their pelts [42], they are less able to tolerate hot conditions [5]. To minimise thermoregulatory stress, they therefore must limit their activity to cooler periods of the day [19].

The chemical properties of koala food trees may also have influenced activity patterns. Eucalyptus foliage is high in formylated phloroglucinol compounds (FPCs), a group of plant secondary metabolites that inhibit total food intake [8]. Feeding bouts are interspersed with periods of inactivity to allow ingested material to be detoxified, and decline in duration after the first initial bout for the day [43]. The decline in activity after 22:00 h in our study may, therefore, be due to koalas needing to rest to digest food after the first main feeding bout of the afternoon or evening.

Our study has demonstrated the effectiveness of accelerometry for examining activity patterns of the koala. Because of the koala’s highly specialised and energy-poor diet, activity patterns of this species are likely to vary with changes in resource availability, climate variables, and seasonal energy requirements [12]. Accelerometry will therefore be a useful tool for measuring the impacts of anthropogenic- and climate-mediated environmental change on this species. Accelerometry also has potential application to other species and their behavioral adaptation to spatially and temporally varying environments.