Fish sounds were first scientifically studied in North America by Abbot [1] who in 1877 lamented that “the little fishes of our inland brooks and more pretentious denizens of our rivers are looked upon as voiceless creatures…” and concluded that “certain sounds made by these fishes are really vocal efforts….”. Almost 100 years later Stober [2] was the first to describe the underwater noise spectra in relation to freshwater fish sounds in any freshwater habitat in an effort to determine if the sound of streams entering a lake could be used as a homing cue for cutthroat trout. He also pointed out the critical lack of data on the ambient noise and fish sounds in freshwater systems. Fortunately, after long neglect there has been a recent surge in interest in the potential impacts of anthropogenic noise on freshwater ecosystems [see reviews in 3–9], but efforts to understand such impacts are hampered by the paucity of data on the natural soundscape composition [9]. The need for research on the sound production of freshwater fishes was highlighted in our recent review of the literature, which found that sounds have been reported in only 87 species in North America and Europe, but detailed descriptions of sound characteristics are known for only 30 species [9].

Acoustic investigations of freshwater soundscapes can be grouped (S1 Table and citations therein) into those that seek to characterize the ambient noise [2, 10–20], those that focus on the biophony (without reporting on anthropophony) [21–27], those that focus on noise impacts on fishes and other organisms (see reviews in [8, 28–30]), and those that include some information on both the biophony and anthropophony [31–43]. Most of the latter studies focus on sound levels and do not provide information on the relative contribution of both the biophony and anthropophony to the soundscape in terms of percent occurrence, number of sounds, percent of time occupied, or diversity (except [31,32, 35,36, 40] S1 Table). No freshwater study provides data on the rate of temporal overlap between anthropomorphic and biophonic sounds (i.e., how often do fish sounds overlap with anthropogenic sounds?). Descriptive studies that characterize the soundscape of freshwater habitat including the relative contribution of both anthropogenic and biophonic sounds to the soundscape composition are needed. Furthermore, only a few studies incorporate some level of real-time acoustic monitoring into the sampling design (S1 Table, [2, 23, 27, 31]).

Previous studies of the biophonic component of freshwater habitats in the New England region of North America include species-specific studies [23, 44,45] and a soundscape survey of the Hudson River [31]. Martin and Popper [42] conducted a survey of the noise levels in the vicinity of the Tappan Zee Bridge in the Hudson River, but did not quantify the occurrence of biophonic sounds.

The present study is part of a series of studies seeking to document the soundscape composition of habitats in New England. In a pilot study focusing on fish sounds in the Hudson River a high diversity of known and unknown biological sounds was discovered [31]. At a location in New York City, arguably one of the world’s most impacted locations, a high diversity of mostly unknown biological sounds was heard at night likely resulting from a combination of increasing nocturnal sound production and decreasing masking from boat noise [31]. The value of reporting information on unknown biological sound occurrence was emphasized after the discovery that one of the unknown sounds in the Hudson River was produced by the invasive freshwater drum, Aplodinotus grunniens [44].

Following the Hudson River study, this study was conducted to document the soundscape of a wide range of habitats within the New England region. Because real-time monitoring was conducted during all recording, it was possible to notice that some of the most common sounds appeared to be of the little understood air passage type. It was, therefore, necessary to conduct a series of surveys over the next ten years to identify some of the air passage sounds and to confirm that they could confidently be attributed to fish [45]. Air passage sounds, which hereafter are referred to as “air movement” sounds, are produced by internal movements of gas to and from the gas bladder, or release of gas through the mouth, gill, or anal vent in physostomous fishes [45]. The best-known air movement sound is the “fast repetitive tick” (FRT) type which consists of a broadband high-frequency burst followed by a train of repeating ticks [45]. This new understanding of air movement sounds occurring in freshwater fish allowed us to reprocess recordings collected in the 2008 study in order to classify sounds into broad biological sound types.

The primary goals of this study were to document the occurrence of biological sounds in a large variety of freshwater habitats over a large geographic area and to determine the relative contribution of broad categories of both biological and anthropogenic sounds to the overall aquatic soundscape composition.

A total of 4,825 biological, 1623 anthropogenic noise, and 834 unclassified sounds (Table 1) were measured from 2,750 minutes of recording in 173 locations (S2 Table). Examples of some of the most common air movement sounds are described elsewhere [45]. Examples of traffic, train, running boat and other boat noises are provided in S2–S5 Figs together with their corresponding sound files (S2–S5 Audios). An example demonstrating likely masking of other fish, other air movement, and FRT sounds by traffic noise can be viewed in S2 Fig and heard in S2 Audio. These examples are provided to demonstrate the temporal variation in frequency content and relative sound level change within the sound type.

In general, anthropogenic noises were 1 to 2 orders of magnitude longer in duration than biological sounds and exhibited consistent spectral overlap with them (Fig 2, Table 1, S6 Fig). FRTs, insect and bird sounds had the longest durations of the biophony averaging 2–3 s, while boat, plane and train sounds had the longest durations of the anthropophony averaging 28–277 s. Other fish sounds had the lowest peak frequency of the biophony, while insects and birds had the highest (Table 1). Traffic sounds had the lowest mean peak frequency and fishing and other boat sounds had the highest peak frequency of the anthropophony. Train sound peak frequency was inflated by whistle sounds, and otherwise would have the lowest peak frequency (S6 Fig). Peak frequency of ambient noise was below that of most biophonic sounds but overlapped strongly with traffic and other anthropogenic noises (Fig 2, Table 1, S6 Fig).

Biophony occurred in 57% and anthropophony occurred in 63% of the locations (Table 2). Other air movement sounds were the most frequently occurring (39% of locations) component of the biophony followed by other fish (30% of locations). Air movement sounds were dominated by high-frequency sounds similar to those previously described [45] for salmonids (46%), alewife (Alosa pseudoharengus, Clupeidae) and alewife-like sounds (27%), and white sucker-like (Catastomus commersonii, Catostomidae) sounds (8%). Twenty-three percent of FRT sounds were attributed to alewife while the rest were unknown. Most of the other fish sounds were unknown, but 13% were catfish-like sounds most likely produced by brown bullhead (Ameiurus nebulosus, Ictaluridae. [31]).

Biophony was observed in significantly more locations at night than during the day (84% vs 53%, Table 2). All components of the biophony except insect-like and bird sounds occurred in significantly more night locations than day locations. Traffic sounds were the most common component of the anthropophony occurring in 40% of the locations. No significant diel differences in occurrence among locations were observed for the anthropophony.

Other air movement (5%), FRT (7%), other fish (10%), insect-like (9%), bird (11%) and other biological (4%) sounds overlapped in time with traffic sounds. The only other noises to overlap in time with biological sounds were: airplane (0.1% and 0.4%, with other fish and insect-like), other boat (0.1% and 0.3%, with other air movement and other fish), and other noise (0.1% with other fish).

The three most significant findings in this study are: 1) freshwater habitats in the New England region of North America contain a diverse array of unidentified biological sounds; 2) air movement sounds constitute an important component of freshwater soundscapes; and 3) anthropogenic noises dominate the soundscape and their overlap in time and frequency with the biophony, together with their high sound levels, suggests a high potential for negative impacts. The impact of anthropogenic noise on the natural freshwater soundscape is most strongly illustrated in Fig 4 which demonstrates the prevalence of the anthropophony accounting for 90% of the soundscape by relative mean percent time. This finding alone signals how dramatically freshwater soundscapes have been modified by human-produced noise. The strong spectral overlap between the biophony and anthropophony further hints at potential impacts (Fig 2). However, masking only occurs when individual biophonic sounds overlap in time and frequency with individual anthropophonic sounds. Assuming no bias in detection, high rates of temporal overlap with the biophony were only found with traffic noise (ranging for 4% to 11% depending on the biophonic category), while if detection was biased, then the overlap is underestimated. It should be pointed out that any sound level of anthropophonic noise in these habitats alters the soundscape from that in which aquatic organisms have evolved. The potential for impact is further supported by the observed higher sound levels of anthropophony sources compared to biophony sources (Fig 6 and S6 Fig). Finally, the highly significant decline in the frequency of occurrence (Fig 5, S7 Table), number and percent time of sounds (S8 Table), and diversity (S12 Fig) of the biophony with increasing ambient received sound level suggests that high noise levels, whether natural or anthropogenic, can affect sound production and soundscape composition (although bias from masking of sound detection must be considered as discussed below).

Our observations of the widespread occurrence of air movement sounds in many habitats across a large geographic area, together with their large contribution to the biological soundscape based on sound rate and sound percent time, suggest for the first time that air movement sounds are an important phenomenon in multiple types of freshwater habitats. We emphasize that even if air movement sounds are largely incidental, if sounds are species specific [45], they can be used by scientists and resource managers as an aid in documenting the spatial and temporal distribution of fishes and their associated soniferous behavior [49]. In addition, we point out that even incidental sounds can expose an organism to predation by organisms that can hear that sound, and hence would be subject to natural selection pressures.

Despite the lack of significant habitat differences in ambient noise levels, sound level appeared to have a strong negative influence on biological diversity and soundscape composition (Fig 5, S7 and S8 Tables), suggesting possible masking, suppression of sound production, or avoidance of locations with high ambient noise levels regardless of their source. A negative effect of ambient noise level on biological sound production or detection supports previous work on potential impacts of noise levels on freshwater fishes [e.g. 10–11, 13, 20, 25, 37 and review in 7], however we caution that the results do not necessarily suggest the observed trend was due to purely anthropogenic noise effects since no biological sounds were negatively correlated with any noise rate or percent time variable. The lack of such correlations may simply be due to the high diversity of sounds observed while sampling over a wide variety of habitats and geographies with many different faunal assemblages. The overlapping frequency structure of anthropogenic noises with the biophony, especially with the other fish category (Fig 2, S6 Fig, Table 1) also suggests the potential for masking (an example of which can be seen in S2 Fig and the corresponding S2 Audio). In contrast, the lack of overlap between peak frequencies of biological sounds and peak ambient frequency (Fig 2, S6 Fig) lends further support to previous studies suggesting that fish take advantage of acoustic niches [e.g. 25]. Our data suggest that a high-frequency “quiet noise window” may also occur in other freshwater habitats, and that freshwater organisms may have evolved to exploit different acoustic windows in different habitats. It is also possible that multiple acoustic windows may occur in some habitats which can be exploited by different organisms. The impact of anthropogenic noise on the natural noise windows in various habitats remains poorly understood.

Running boats generate long-lasting noise starting with low-amplitude and low-frequency noise while in the distance and progressing to high-amplitude noise that saturates the recordings when within a few hundred meters (depending on the boat type and speed), before gradually fading as the boat moves off in the distance again (an example of the sound of an approaching boat which anchors within 100 m of the recording site is provided in S4 Fig and corresponding S4 Audio). Boat noise in excess of 90% time were observed at some locations (S1 Data set), highlighting the potential of boat noise as a masking source in freshwater. Similar observations have been reported in freshwater [32] and marine habitats [e.g. 50–52]. Smott et al [51] reported three types of boat sounds: burst broadband, variable broadband, and low frequency, which likely correspond with our other boat, running boat, and idle boat categories. Locations near important navigation routes, marinas, or boat landings experience chronic boat noise exposure. In some cases, boat noise is so prevalent in the hours around sunset (when boaters are returning to shore) that recording of biological sound is nearly impossible. Our sampling was conducted during the early season when boating activity was sparse and many boat ramps had not yet opened for the season. We would expect, therefore, that boat noise would be significantly more prevalent during the summer months than that observed in our study, similar to reports from marine systems [e.g. 50–52]. Boat noise was undoubtedly an important chronic noise source in navigable waters where it dominated the soundscape and unquestionably masks many biological sounds (Fig 6, S4 and S6 Figs). Boat noise is particularly problematic in enclosed water bodies such as small lakes, and in linear rivers as the sound travels great distances. We have often detected motor boat sounds before sighting the vessel in the distance. On the other hand, serpentine waterways may be less impacted because sounds of an approaching vessel are blocked by land until the vessel moves around the bend and into the line of sight.

Our observations suggest that boats running idle while docked, anchored, or drifting are a major component of freshwater soundscapes (Fig 4), and have the potential to mask some biophony such as insect sounds, but we are not aware of studies that examine its potential impact in freshwater. However, at least one study in a small estuarine river reported boat sounds attributed to idling to be important masking sources for sciaenid fishes [51]. The tendency for boaters, and especially ferries and other large vessels, to idle for long periods, and the lower frequency structure of idling boats (Figs 2 and 6, S6 Fig) suggests that boat idling may be an important chronic noise source in navigable waters. Power density spectra of boat sounds in this study were remarkably similar to those reported in other freshwater [e.g. 10, 42] and marine studies [e.g. 51].

Traffic noise exhibits similar though much less extreme wax-and-wane patterns as can clearly be seen in S2 Fig and heard in the corresponding S2 Audio. Our observations support those of previous researchers that traffic sounds can be important in some freshwater habitats [34–38, 41–42]. Holt and Johnston [37] measured traffic noise propagation distances in streams and concluded that traffic sounds may have negative impacts in freshwater habitats. In contrast, ice road traffic (with similar signatures to our traffic sounds) were not thought to impact burbot (Lota lota, Gadidae) under the ice in Great Slave Lake, Canada [41]. Hopson [38] found evidence of traffic impacts on both the above and below water biophony in freshwater wetlands of Ohio.

Although not as extreme as boat noise, traffic sounds are far more ubiquitous in freshwater habitats and can be chronic in urban areas and during rush hours. In fact, the increase in traffic contribution to the soundscape at night was due in part to our sampling around sunset when traffic tends to be heavy. The relatively high temporal overlap between biological sounds and traffic sounds suggests a high likelihood for impacts, especially for other fish sounds which had both high temporal (10%) and acoustic frequency overlap (Figs 2 and 6, S6 Fig). A comparison of the power density spectra of traffic sounds with the biophony (Fig 6, S6 Fig) suggests they would likely mask all but the other fish category. Although we did not examine propagation distances of traffic sounds, traffic crossing bridges was detected in locations as far as 270 m from the nearest bridge (S1 Data set), agreeing well with previous studies [37, 42]. Differences in the relative contribution of traffic and boat noises to the soundscape among habitats and river regions demonstrate variations in potential noise impacts among habitats and river zones (S9 and S10 Figs, S5 and S6 Tables). It should be recognized that traffic sounds were likely over-represented in our sampling due to the frequent necessity of accessing the water near bridges. However, as has previously been pointed out [37], in many areas bridge crossings are common and smaller streams and rivers may be crossed many times over short stretches in urban and suburban locations.

The inconsistent trends in observations moving along the river main stem locations likely result from the fact that river systems form a coenocline where gradients in abiotic and biotic conditions regulate community structure and habitat function [53]. Thus, comparison among river systems of different lengths and elevation gradients requires a gradient approach. To our knowledge this is the first study to examine river order changes in freshwater soundscapes, although differences in ambient noise levels have been compared among rivers [17, 19] and along short reaches of rivers [18]. Major differences in the soundscape were previously found between two locations in the Hudson River [31]. The only other study to examine the biophony of multiple locations within the same freshwater river, found significant differences among tributaries classified by degree of connectivity [22].

It is interesting that while the biotic community changes considerably from high elevation reaches to estuarine reaches, the changes in the biophony type contribution to the soundscape are minimal, suggesting that although soniferous species may change, the broad sound categories are more consistent. Classification of sounds to more specific sound types would likely have resulted in significant differences in the soundscape along the river coenocline due to species assemblage changes as it has been shown in a series of studies in a small estuarine river [51, 54–56]. A gradient in impacts from different types of anthropogenic noise is expected as we observed a striking transition from remote wilderness to increasingly developed urban areas while traveling from the river headwaters to the sea. Some of this transition was captured in the comparison between non-tidal and tidal reaches of the rivers where there was a shift between dominance of the soundscape by traffic noise in non-tidal reaches to a dominance by boat noise in tidal reaches (S10 Fig, S6 Table), highlighting different potential for impacts in different habitats.

Studies on the biophony of temperate freshwater habitats have used a variety of methodologies from point sampling to long-term sampling (S1 Table). Studies in rivers have reported 21 [31], 25 [26], and 128 [22] biophonic sound types. Similar numbers have been reported for ponds (48 [4]) and lakes (26 [43]). Except in single species studies, in most cases biophonic sound sources are unknown. As we pointed out in our review of sound production in temperate freshwater fishes [9], there is a critical need for studies to describe fish sound sources in freshwater habitats. Our use of real-time monitoring resulted in the detection of a high diversity of air movement sounds that would likely have been overlooked if the recordings had only been analyzed in post-processing (see S1 Audio for an example). In addition, real-time monitoring allowed us to identify false biophonic sounds such as creaking logs, twig rattling, and floating dock squeaking that appear very similar to biophonic sounds in their acoustic characteristics.

Freshwater habitats are highly impacted by terrestrial and aerial sound sources. Bird sounds are one component of the soundscape that may have important effects on fish behavior. For example, herring gull sounds are clearly audible underwater in herring runs, and are likely audible to alewife [45]. Other terrestrial sounds have similar potential ecological interactions. We advocate for studies that simultaneously record above and below water sounds [38–40, 57] to distinguish between above and below water sound sources, but ultimately to describe what we refer to as the “holo-soundscape” of freshwater systems. Kuehne et al [40] attempted to correlate above and below water sound recordings, but unfortunately defined the biophony as sounds from 3–8 kHz and the anthropophony as sounds of 1–2 kHz which confounds the two sound sources, given that many fish sounds would fall in the lower frequency bandwidth. Hopson [38] reported higher sound intensity, more anthropophonic sound occurrences, and lower acoustic diversity in both above and below water wetland soundscapes in disturbed versus non-disturbed areas.

Recent developments in acoustic sensor technology (e.g. long performance dataloggers) and of automated processing methods (e.g. automatic recognition methods and acoustic indices) now allow researchers to relatively inexpensively collect long-term recordings and to process them in timeframes which are unattainable by more traditional recording and analysis approaches (e.g. manual and aural quantification of sound occurrences) [4]. These developments are rapidly expanding the field of passive acoustic research and have the potential to quickly identify biophonic patterns and anthropophonic impacts on them [4]. However, as the biophonic component of most aquatic habitats is still poorly understood, the application of automated processing methods alone, without a prior knowledge of the type of signals present in a specific site, might result in interpretations that do not accurately reflect the biodiversity and the ecological status of the area. Efforts to identify specific sound sources in freshwater soundscapes are, therefore, critically needed. Attempts to correlate unknown sounds with the presence of macroinvertebrates (e.g. [13, 22, 35–36]) or fishes [2, 23–24, 27, 32] are especially helpful. Follow-up studies that attempt to identify the unknown sound sources are also important (e.g. [23, 31, 45]). Unfortunately, few studies incorporate real-time monitoring of sounds (S1 Table, [2, 23, 27, 31]). A series of studies in the estuarine May River of South Carolina [51, 54–56] demonstrate the advantage of having well documented sound sources when attempting to examine anthropophonic impacts and ecological influences on the underwater soundscape. Whenever possible when beginning a research program in previously unstudied freshwater habitats, researchers should attempt to conduct preliminary studies utilizing real-time sound monitoring and visual observations of the holo-soundscape, together with faunal sampling and field-auditioning of aquatic organisms before, or concurrently with, the collection of long soundscape sound series.