This study was conducted at two sites in New Zealand. The first, Patersons Terrace (Fig 1A), is an unused gravel road situated ~8 km SW of Tekapō. It is not known when or how B. robustus colonised this site. The road substrate is comprised of gravels (small stones < 64 mm Ø) and larger cobbles that have been compacted by historical heavy vehicle use. Vegetation is sparse and consists mostly of lichens and low stature vascular plants such as Raoulia australis and hawkweed (Hieracium spp. and Pilosella spp.), as well as occasional Rosa rubiginosa and exotic grasses. The gravel habitat is bordered by semi-modified grasslands dominated by fescue tussock (Festuca novae-zelandiae) and exotic pasture grass [36]. Permission to access Patersons Terrace was granted by Genesis Energy and Land Information New Zealand (LINZ).

The second site, Snowy River (Fig 1B), is an alluvial fan with braided river characteristics which flows intermittently throughout the year. Brachaspis robustus are established on the lower braided section (~ 600 m wide). Occasional flooding events disturb the riverbed and remove vegetation. Mosses, lichens and herbaceous plants (e.g., introduced Viper’s bugloss, Echium vulgare), establish quickly after flooding events, and larger woody plants (e.g., R. rubiginosa) are present on more stable sections of the riverbed. Substrate size is diverse and includes fine sands, cobbles and large boulders. Permission to access Snowy River was granted by Grampians Station.

Plot and transect searches of equal area were compared at Patersons Terrace during the austral summer (November to March) for three consecutive seasons (2015–2018). Three 100 m x 1 m (100 m²) transects, spaced ~1 km apart, were marked out along the centre of the gravel road. Along each 100 m transect, four evenly spaced 5 m x 5 m (25 m²) plots were defined on alternating edges of the road using metal corner pegs. Henceforth, a group of 4 plots (equal to 100 m²) is referred to as a “plot unit”. The plots and transects remained in the same location over the duration of the study.

Transect searches were conducted at Snowy River during the second (2016–17) and third (2017–18) seasons only. Three 100 m x 1 m transects spaced > 200 m apart were set up longitudinally along the riverbed in locations where grasshoppers were known to occur. Transects were marked with plastic pegs placed at 20 m intervals. In the third season, two additional 100 m x 1 m transects were set up at the site. The three original transects were set up as close as possible to their initial location. However, changes in channel morphology resulted in minor deviations of less than 8 m.

Monitoring took place from November to March each summer on days of suitable weather (ground temperature > 13.6°C and not during gale force winds or precipitation). Each transect and plot unit was searched on at least 6 days per month when feasible (Patersons Terrace, mean visits per month = 6, range = 2 to 8; Snowy River, mean = 5.5, range = 3 to 7) but the number of monthly searches achieved and duration between visits (1 to 11 days) varied according to the occurrence of favourable weather. All plots and transects were searched by the same observer throughout the study. Both sites were searched on the same day except where weather was not permitting (e.g., rain at one of the sites). Prior to commencing a search, barometric pressure, air temperature at 1 m above the ground, and ground surface temperature in the shade were measured using a Kestrel 3500 Pocket Weather Metre (GeoSystems New Zealand Ltd). Cloud cover (categories: none; high cloud, when cloud was high in the sky but did not cause shadows; patchy cloud, when clouds were lower in the sky and caused shadows; overcast) and start time were recorded for each search. During the search, the observer walked slowly sweeping their front foot over the ground in front of them and moved in a direction such that their shadow fell on the area already searched. This method made visual detection possible by eliciting a jump response from the grasshopper. When detected, grasshoppers were captured, their body length (from the top of the head to the tip of the abdomen) and femur length measured, and sex and transect location recorded. Each grasshopper was then released behind the observer to ensure it was not re-counted, and the remainder of the area was searched. The minimum time required to complete a search of a 100 m² transect was 5 mins, and for each plot was ~1.5 mins (~6 mins per 100 m² plot unit including time taken to walk between plots) but this increased with the number of grasshoppers found. During this study, adulthood was determined by measuring hind femur length. Females with a femur length of ≥ 15 mm, and males with a femur length of ≥ 9 mm were considered adults. Individuals less than 8 mm in body length were excluded from the study because the risk of causing a fatal injury during capture and handling was too high. Permission to handle a Threatened species for the purpose of this research was provided by the Department of Conservation, New Zealand (DOCDM-1528162).

The number of individuals counted using transects was on average 8% lower than counts from plots, but the difference was not significant (p = 0.32). On average, there were significantly more grasshoppers counted in January than December (p < 0.001) and November (p < 0.001), and in March than November (p = 0.03). No other pairwise comparisons between months were significant (i.e., p > 0.05). Season 1 and 2 counts were not significantly different (p = 0.46) but counts in season 3 were on average 41% lower than season 1 (p < 0.001), and 47% lower than season 2 (p < 0.001; Fig 2).

On average, searches using transects detected 6% fewer adult females than did plots, but the difference was non-significant (p = 0.87). Counts were not significantly different between November and December (p = 0.15). There were significantly fewer adult females detected on average in season 3 than season 1 (p = 0.004), but the differences between seasons 2 and 1 (p = 0.11), and 3 and 2 (p = 0.26) were non-significant (Fig 3). There was no significant difference in the Index of Dispersion for full population data collected using plot searches, or transect searches at either site (F_(2,92.2) = 1.71, p = 0.19).

At Patersons Terrace, we estimated the adult female grasshopper density in November to be 0.5 individuals per 100 m² in season 1 (n = 2 temporal replicates), 0.14 (n = 7) in season 2, and 0.17 (n = 6) in season 3 at Patersons Terrace, and 0.44 (n = 3) in season 2 and 0.07 (n = 6) in season 3 at Snowy River. The power to detect a significant change (p < 0.05) in population size at Snowy River when monitoring adult females in November and December was low for all combinations of transect counts and repeated visits modelled. At Patersons Terrace, power of 0.8 could be achieved using a minimum of 7 transects and 10 repeated visits, or 17 transects and 4 repeated visits. Power was much higher for both sites when all demographics were included in counts in February (Fig 4).

Grasshopper counts generated from plot searches and transect searches at Patersons Terrace did not differ significantly, although mean plot counts were slightly higher. We expected a greater difference given transects had 202 m of exposed edge per 100 m² search area, compared to 80 m for plots, meaning opportunities for grasshoppers to enter and exit the search area during the monitoring event were much higher during transect searches. Additionally, during a plot search the observer’s direction of movement loops back and forth within the plot, meaning they spend more time within a grasshopper’s jump range. This provides more opportunities for accidental double-counting to occur and could have artificially inflated counts relative to the transect method where grasshoppers are released behind the observer. In this study, we believe the above effects were minimised by short search durations and the small area of the plots that allowed the observer to keep track of individual grasshoppers and avoid double-counting. However, when monitoring species with extremely low densities, double-counting could cause significant errors in trend data. For B. robustus, we found the mean density of adult females to range between 0.07 and 0.5 individuals per 100 m². Double counting of even a few individuals could artificially inflate population density estimates to the point that a false trend might be generated. For threatened insects, falsely inflated population estimates and/or obscured population trends could have significant implications if they were to result in management delays or complete inaction when it is needed.

Conducting threatened species monitoring in locations where key resources of the target species occur is an important consideration. Retaining static transect locations for multiple years might be suitable for species that inhabit relatively homogenous environments, such as grasslands, or are associated with specific host plants with a stable distribution, but it could be problematic if the underlying resource distribution shifts and transect locations do not reflect that change [42]. For terrestrial braided river insects like B. robustus, one of the most significant changes in resource distribution will be associated with seasonal changes to channel morphology driven by flooding events. For example, the braided river grasshopper Bryodema tuberculata persists as metapopulations, where flooding or succession causes local extinctions that are compensated for by the recolonisation of new gravel bars [43]. Flexibility in search locations is vital to avoid mistaking a change in distribution of the species in the landscape for a sudden decline in population density.

When implementing monitoring over larger areas, it is likely that an observer will use a GPS to navigate rather than static markers as used here. A transect search only requires navigation between two points. A plot search, in contrast, would require navigation back and forth multiple times without crossing the same path, which is much more difficult to achieve (pers. obs.) and has a higher risk of double-counting individual insects. Given little difference in counts or search time were found between plot and transect search methods in this study, a transect method is therefore recommended for monitoring B. robustus population density to reduce the risk of artificially inflated counts.

The importance of temporal replication during insect monitoring (i.e., multiple visits within a single season) was highlighted by several of the density estimates that we presented here for B. robustus. Density estimates for adult females in November at Patersons Terrace were similar in 2016 and 2017 when searches were replicated ≥ 6 times. When only 2 replicates were performed in 2015, the estimate was ~3 times higher. Similarly, at Snowy River, density estimates from adult females were ~6 times higher when only 3 visits were made compared to when 6 visits were made, and the same was true when adults and nymphs of both sexes were counted. Although an underlying annual effect on insect population size is to be expected (given the seasonal variation in temperature and other climatic influences), discrepancies of this magnitude are most likely to arise from detection variability, which is more prevalent when fewer temporal replications (visits) are undertaken [44].

Species phenology is a crucial consideration when making decisions about the design of threatened insects monitoring, particularly when the species is hemimetabolous and both nymphs and adults are present at the same time and difficult to distinguish (as is the case for B. robustus). We found that the power to detect significant change in population size was high when monitoring was conducted in February, even when there were as few as 5 transects visited 3 times. However, in February most of the B. robustus population is comprised of nymphs that are small in body size, have low probabilities of visual detection [27] and may be difficult for inexperienced observers to distinguish from other species [28]. Furthermore, grasshopper nymphs, and the juvenile stages of insects in general, typically have high rates of mortality [45], and for most threatened insects the relationship between nymph and adult numbers, and therefore recruitment, is unlikely to be known. We recommend that population density monitoring for B. robustus should index population size based on the relative density of large female grasshoppers, because they have the highest rates of visual detection and are representative of the breeding population [27]. Despite the fact that counts of large females were low, we found that monitoring using 20 transects (spatial replicates) and 4 visits (temporal replicates) per season provided sufficient power (> 0.8) to detect a significant (p < 0.05) change in population size at Patersons Terrace. Monitoring protocols reported for other threatened insects are also often restricted to the adult demographic, but most published examples are less complex because the species are either holometabolous (e.g., butterflies [9], beetles [46, 47]) or have aquatic nymphs occupying a different habitat (e.g., damsel- and dragonflies [48]) so that juveniles and adults cannot be confused; or they are hemimetabolous insects that are univoltine with synchronised development, or obviously winged (e.g., Crau Plain grasshopper [49]) and again adults and juveniles are unlikely to be confused.

In this study we demonstrated the development of a practical density monitoring protocol for the population of B. robustus present at Patersons Terrace, an un-used gravel road habitat. Our findings were not transferable to the population present at Snowy River, a natural braided river habitat. We found that the power to detect change in density of the large female demographic at Snowy River was very low, likely because our simulation was based on only 2 seasons of data that contained a high proportion of 0 counts. These low counts could indicate the population density is lower at Snowy River, but more likely they reflect poorer detectability in that environment. A review of methods for monitoring common grasshopper species in grasslands found that transect searches were accurate when the species occurred at low densities of less than 2 adults per m² and in low open swards (versus higher densities and/or taller swards) provided environments were homogenous and movements into and out of the search area during the search period were minimal [50]. Patersons Terrace conforms to these requirements by design, as the substrate is uniform and compacted from historic vehicle use (i.e., relatively homogenous), and the habitat is narrow minimising the number of grasshoppers present on either side of a transect (i.e., low migration to/from search area). In contrast, Snowy River is a relatively expansive, active riverbed that provides a dynamic, heterogenous and refuge-rich habitat. These fundamental differences in habitat structure are likely to produce substantially different detection rates of large females during monitoring events.

Understanding the difference in the power to detect population density change between the two sites monitored here is crucial to the design of monitoring protocols for B. robustus, because the few remaining populations of the species can be broadly categorised as occupying two physically different habitats. Those that occupy relatively homogenous modified habitats, including Patersons Terrace, are easier to study and protect. The remaining populations occupy more natural riverbed habitats. These are more difficult to manage but are crucial to the persistence of the species in its natural range. To date, few targeted surveys have been undertaken for the riverbed populations and as a result there is little information on the grasshopper’s true current distribution. However, observations during regular management of other riverbed species suggest population contraction and increased distances between patches on the larger rivers. The data presented here indicate that monitoring to inform management of riverbed populations will likely need to be much more intensive than what is required at Patersons Terrace. Given resources for insect conservation globally are often extremely limited, practitioners will benefit from being flexible in the effort directed to monitoring at different sites to meet their conservation objectives, rather than taking a ‘one size fits all’ approach.

In general, when the probability of detection is high, fewer visits to a site are required to have confidence in the presence or absence of a species [51]. We found that the probability of detecting a grasshopper (p_g) was higher at Patersons Terrace than Snowy River using either a 100 m or 20 m long transect. However, we could not tease apart whether this was a population density or habitat structure effect. If grasshopper density was higher, we would expect the probability of detection to be higher. This logic explains why p_g is higher in the months following nymph emergence, despite small juveniles having lower individual detection probabilities [27]. Alternatively, as mentioned above, p_g could also be higher at Patersons Terrace because the substrate is comprised of small, uniform and highly compacted gravels, and vegetation stature is low, so there are fewer refuges for grasshoppers to retreat into when disturbed by an observer. In contrast, Snowy River has diverse substrate size and seasonal riverbed disturbance creating interstitial spaces, as well as a higher diversity of vegetation, including both tall woody weeds and low leafy herbaceous plants that could conceal grasshoppers much more than the compact mat plants found at Patersons Terrace.

Conducting monitoring when probabilities of detection are high can provide greater confidence in monitoring results [10], particularly when the number of search replicates conducted is limited. One way to maximise detection probabilities is to restrict searches to when weather conditions are most favourable for detection [52]. In this study we found that cloud cover had a significant effect on the probability of detection. Because a jump in response to observer disturbance is usually required for detection to occur, monitoring that takes place on fine days will yield higher detection probabilities as grasshoppers are able to bask and raise body temperature, therefore increasing activity [53]. Although temperature was not found to be a significant predictor of detection probabilities in this study, it is usually a vital parameter for monitoring other insects, such as butterflies [52], and in this case might indicate that all our monitoring was conducted within the thermal thresholds for normal activity.

Mackenzie and Royle [51] recommend that a minimum of 3 visits be made when p_g > 0.5. Low p_g was yielded in both sites when using a 20 m² transect, but a high p_g (> 0.6) was achieved at both sites using a 100 m² transect under ‘no cloud’ conditions. However, the Patersons Terrace and Snowy River populations of B. robustus are expected to be the densest [25], and largest [26], across the species range respectively, so p_g is expected to be lower at other sites. We recommend that to monitor B. robustus distribution at a landscape scale, a minimum of 3 visits be made per season to transects ≥ 100 m in length during fine warm weather, and that visits occur in February when probabilities of detecting a grasshopper peak.