Analysis of Lake Shoreline Evolution Characteristics Based on Object Increments

Abstract

Evolutionary changes in shallow lake shorelines can significantly impact wetland biodiversity transformation. This paper aims to further elucidate the wetland evolution process by investigating the temporal and spatial characteristics and rules governing lake shoreline evolution. Departing from traditional analyses of wetland area and shoreline length changes, this paper presents a comprehensive approach to quantifying typical lake shoreline evolution patterns using the concept of object increments. These evolutionary patterns are classified into four types: “expansion”, “shrinkage”, “appearance”, and “disappearance”. Using Shengjin Lake as a case study, Landsat images from 2001 to 2020 were used to extract the lake shoreline. The temporal series characteristics of different evolution patterns, the laws at the patch scale, and the characteristics of evolution direction were analyzed. The key findings are as follows. (1) The evolution of Shengjin Lake’s shoreline from 2001 to 2020 was primarily characterized by “expansion” or “shrinkage” patterns with a clear negative correlation between them. The “appearance” and “disappearance” of lake shorelines were rare. (2) The evolutionary patterns of “expansion” or “shrinkage” mainly occurred in smaller patches with a large number, while the “appearance” and “disappearance” of lake shorelines occurred mostly in larger patches with a small number, and there were no occurrences in certain years. (3) The “expansion” evolutionary pattern was more dominant in the northeast and east-by-northeast regions, while the “shrinkage” evolutionary pattern varied across the southwest and west-by-southwest regions. In conclusion, the analysis of shoreline evolution’s temporal and spatial characteristics, based on spatiotemporal object increments, can quantitatively elucidate the lake wetland evolution process and offers a novel perspective for future research on lake wetlands.

1. Introduction

The wetland shoreline serves as a transitional zone between aquatic and terrestrial ecosystems, facilitating the exchange of material, energy, and information [1,2]. This exchange plays a crucial role in connecting these two ecosystems [1,2]. Shoreline dynamics are intricate and ever-changing spatial processes, encompassing the ecological interactions between land and water [3,4]. The proportion of open water and the lakeside zone significantly influences the patterns of the lake wetland landscape, driven by fluctuations in the lake shoreline. This relationship between wetland landscape patterns and ecology is significant, particularly regarding the impact on species habitats. The habitat quality for organisms that are dependent on the lake ecosystem is directly influenced by the relationship between wetland landscape patterns and ecology which subsequently affects the decisions of aquatic birds and other higher trophic organisms regarding roosting, foraging, and nesting within the area [5,6,7].

Significant alterations in the lake shoreline, whether through substantial expansion or contraction, can lead to profound transformations in the natural habitat, potentially resulting in a severe reduction or complete loss of habitat for rare wildlife [8,9]. Therefore, understanding the temporal and spatial characteristics of lake shoreline changes and uncovering the underlying ecological implications of such changes are fundamental for the accurate execution of wetland management strategies [10]. Over recent decades, various natural and anthropogenic factors have contributed to significant changes in wetland ecosystems. These factors include intensified climate change, an increased frequency of extreme weather events, agricultural expansion, urbanization, and the construction of water management infrastructure, such as sluices, canals, and flood dikes. Additionally, shifts in agricultural irrigation demands have accentuated the issue of wetland disturbance, particularly in relation to changes in lake shorelines [11,12,13].

The evolution of wetland shorelines is characterized geometrically by significant changes over time in wetland area, geometric shape, and spatial position. Acquiring accurate shoreline information forms the foundation for measuring the temporal and spatial evolution characteristics of wetland shorelines [14]. The continuous enhancement in the temporal and spatial resolution of satellite remote sensing technology has facilitated the monitoring of long-term dynamics and the measurement of the evolutionary processes of wetland shorelines. Baschuk et al. used satellite images to evaluate the response of large plants to water level changes in the Saskatchewan River Delta region of Manitoba [15]. Seekell et al. examined the 40-year changes in the Saint Lawrence River estuary reed swamp using IKONOS satellite images and aerial photographs and assessed their impact on water birds [16]. Wang et al. detected shoreline changes in China’s coastal wetlands using a sequence of Landsat images [17].

Quantitative analysis of the spatial and temporal characteristics of shoreline evolution is vital to accurately comprehend the evolution patterns of wetland shorelines. Typically, metrics such as shoreline length and wetland area can directly measure the evolution characteristics of shorelines. Moreover, the number and structural changes of different shoreline types derived from refined shoreline classification are important reference indicators. For instance, wetland shorelines can be categorized into natural and artificial shorelines according to their origin. Moreover, according to their physical composition, they can be further subdivided into categories such as bedrock shorelines, sandy shorelines, and silt/muddy shorelines [18]. Scholars have frequently employed the number and structural changes of different shoreline types as features of shoreline evolution. Second-order indicators such as “change intensity” and “endpoint velocity” are also commonly used to analyze shoreline evolution features through linear or nonlinear combinations of first-order indicators such as shoreline length and wetland area [19,20]. Owing to the complexity of shoreline analysis, the United States Geological Survey has developed the Digital Shoreline Analysis System to assist researchers in quantitatively analyzing shoreline evolution processes [21]. However, the aforementioned analysis methods and tools do not fully consider the complex spatial and temporal evolution processes caused by wetland expansion or contraction, nor do they address the appearance and disappearance of small wetlands.

In the theory and methodology of spatiotemporal object increments, geospatial objects that have changed at a new point in time are used to track all geospatial objects that have undergone changes or have remained unchanged from an old point in time to the new time, thus creating a comprehensive snapshot at the new time. Chen Jun, Lin Yan, and others utilized the object increments model to swiftly detect and explain the spatiotemporal changes in river morphology [22,23]. Similarly, other researchers have applied spatiotemporal object increments to rapidly detect changes in lake and river complexes. Nonetheless, only a few studies have employed spatiotemporal object increments to quantify the temporal and spatial changes of lake shorelines [24,25]. The fundamental unit of landscape patterns is landscape patches, and the number of these patches directly reflects the level of landscape fragmentation [26,27]. The analysis of landscape patch changes can offer theoretical support for studying the crucial factors influencing species habitats [28]. Therefore, taking Shengjin Lake as an example, we utilized long time-series remote sensing data spanning from 2001 to 2020. Employing the theory and methodology of spatiotemporal object increments, we examined the spatiotemporal characteristics of the evolution of lake landscape patches. Our focus encompassed the classification of shoreline evolution patterns according to spatiotemporal snapshot differences, the quantitative spatiotemporal features of various evolution patterns, and the analysis of evolutionary trends. These efforts provide a fresh perspective for uncovering the evolutionary laws governing lake shorelines.

Patterns of lake shoreline evolution hold significant implications for the landscape arrangement and the habitat of species residing in lake wetlands. Studies on the existing analysis methods ignore the complex temporal and spatial evolutionary processes and mostly explore the state of lake shorelines at different stages using snapshot-style sampling, with few investigations into the process of shoreline evolution. In this article, we adopt an object-incremental approach to analyze and quantitatively describe the spatial and temporal characteristics and the evolutionary directions of different modes of change. The outcomes of our study offer valuable insights for comprehending the laws governing the evolution of lake shorelines.

2. Experimental Area Overview and Data Pre-Processing

The experimental area, Shengjin Lake, is situated in Chizhou, Anhui. Shengjin Lake (30°15′ N–30°30′ N, 116°55′ E–117°15′ E) is located at the confluence of Dongzhi County and Guichi District in Chizhou, Anhui. It serves as a representative example of shallow-water lakes interconnected with the Yangtze River in its middle and lower reaches. The lake basin is categorized into upper, middle, and lower sections according to its orientation and shape. The entire lake maintains an average elevation of 11 m, with the middle lakebed is slightly lower than the upper and lower lakebeds. Water flow in the upper and lower lakes is regulated by Jiangba, while the connection between Shengjin Lake and the Yangtze River is facilitated by the Huangpen Dam. The primary sources of water supply comprise atmospheric precipitation and river inflow. Influenced by monsoons, the annual precipitation in Shengjin Lake exhibits considerable variability, with a significant portion occurring during the summer season, accounting for ~50% of the total annual precipitation. Conversely, rainfall is scarce during the winter months. May to August marks the flood season, with an average water level of 12.5 m. November to April of the following year constitutes the dry season, characterized by an average water level of 8.9 m. Other times represent normal water periods, with an average water level of 11.5 m. The variable behavior of the monsoon also leads to significant interannual fluctuations in the water level of Shengjin Lake. Extreme weather phenomena such as El Niño and La Niña also contribute to pronounced shifts in water levels. Shengjin Lake holds great importance as a migration and stopover site for waterbirds along the East Asia–Australasia Flyway. During the winter months, the water level periodically recedes, exposing extensive mudflats. This exposure creates favorable habitats and shelter for waterbirds, attracting numerous migratory birds, such as cranes, storks, geese, ducks, and sandpipers, to spend the winter around Shengjin Lake. Thus, Shengjin Lake is renowned as the “world of cranes” and the “paradise of migratory birds” (Figure 1).

As Shengjin Lake is situated in the plain lake region of eastern China, precipitation predominantly occurs from mid-June to mid-July in normal years. In years characterized by robust summer monsoons, precipitation can extend until August. To mitigate the effects of cloud cover and flooding on the lake shoreline in remote sensing images during rainy conditions, this article avoids the concentrated precipitation period. Instead, Landsat-series remote sensing images captured between September and November from 2001 to 2020 with cloud cover levels below 17% are used to extract the lake shoreline. While cloud cover exceeded 17% in some years, most years experienced minimal cloud interference. Moreover, through the application of cloud removal techniques, we have minimized the impact of cloud cover on lake area measurements to an insignificant degree. The pre-processed remote sensing images were atmospherically and radiometrically corrected to obtain the corrected remote sensing images. The lake shoreline was extracted on an annual basis through manual visual interpretation. First, the water boundary observed when the water level was at its highest point (17.5 m) in Shengjin Lake was used as a reference to crop the pre-processed remote sensing images. Subsequently, the images were standardized to a scale of 1:12,500, with a zoom-in scale of 1:4000 applied to delineate finer details. This process yielded a dataset spanning 20 years of vector data for the wetland shoreline of Shengjin Lake (Figure 1). Second, in ArcGIS software 10.2, the spatial join tool was employed to extract two categories of shoreline evolution—“appearance” and “disappearance”. The intersect tool was then used to capture the overlapping regions between the appearing shoreline and the baseline shoreline. The “expansion” and “contraction” shoreline evolution types were derived using the erase tool, thus generating preliminary snapshot difference information. Finally, through the topological quantization method, a 30 m buffer zone was created around the intersection area. Within this zone, small patches fully encompassed by the buffer were identified as pseudo-changes and consequently eliminated. This meticulous process culminated in the creation of spatiotemporal snapshot difference data, illustrating the evolution of Shengjin Lake’s shoreline over two decades.

3. Materials and Methods

3.1. Classification of Shoreline Evolution Patterns According to Spatiotemporal Object Increments

Spatiotemporal object increments pertain to alterations observed in a spatial object’s configuration between two distinct periods, labeled Oi (t1) and Oi (t2). Similarly, for shoreline snapshots, spatiotemporal object increments denote the differences between the conditions existing before and after specific time intervals. During the evolution of lake shorelines, if water levels rise in subsequent years, the lake’s surface often experiences overflow or the formation of new water bodies, leading to transformations in the lake’s morphology. This can encompass either an overall or localized expansion based on the initial configuration or a departure from the original shape, resulting in the establishment of a novel lake. Conversely, if water levels recede in the following year, the lake contracts or even dries up, potentially causing the disappearance of surrounding wetlands. These modifications in lake morphology can be characterized by four distinct spatiotemporal object increment models: “expansion”, “shrinkage”, “positive difference”, and “negative difference”. The spatiotemporal object increments of lake shorelines can be categorized as “expansion positive difference” and “shrinkage negative difference”, depending on whether an entirely new lake shoreline forms or the entire lake shoreline vanishes.

Table 1. Mapping relationship between the evolution pattern of lake shoreline and object increments.

Object Increments Types	Spatiotemporal Status	Diagrammatic Sketches	Semantics of Object Increments	Evolution Patterns of Lake Shoreline
Expansion positive difference			The lake shoreline expands on the original basis	Expansion
Shrinkage negative difference			The lake shoreline shrinks on the original basis	Shrinkage
Object positive difference			A new lake is completely added, and a new shoreline is formed	Appearance
Object negative difference			A lake disappears completely	Disappearance

illustrates how the spatiotemporal evolution of lake shorelines aligns with the various types of spatiotemporal object increments.

3.2. Extraction Method of Lake Shoreline Evolution Patterns

The three-tuple descriptive model encompassing graph difference (\), difference by (/), and intersection (∩) is used to determine the spatiotemporal object increments, denoted as Oi, from time t1 to time t2. In this context, let G1 and G2 represent the spatial graphs of the target Oi at times t1 and t2, respectively. G1\G2 denotes the portion of the spatial figure belonging to G1 but no longer present in G2, essentially constituting the vanished figure termed “negative difference”. G1/G2 signifies the segment belonging to G2 but not to G1, constituting the added section of the figure referred to as “positive difference” [19]. To accurately differentiate between “expansion positive difference” and “object positive difference” and “shrinkage negative difference” and “object negative difference”, depending on whether G1 and G2 share a common part, the positive difference is divided into “expansion positive difference” (with a shared portion, i.e., G1 ∩ G2 ≠ Ø), aligning with the “expansion” mode of the lake shoreline, and “object positive difference” (no shared portion, i.e., G1 ∩ G2 = Ø), corresponding to the “appearance” mode of the lake shoreline. The negative difference is the “shrinkage negative difference” (a shared portion exists, i.e., G1 ∩ G2 ≠ Ø), aligning with the “shrinkage” mode of the lake shoreline. The negative difference of the target (no shared portion, G1 ∩ G2 = Ø) corresponds to the “disappearance” mode of the lake shoreline. Formula (1) describes the extraction of the four typical shoreline evolution modes based on spatiotemporal object increments.

$$R_3(G_1,G_2)=[\begin{array}{ccc}{G}_1\backslash G_2& G_1\cap G_2& G_1/G_2\end{array}]$$

(1)

3.3. Extraction Methods for Different Evolution Directions of Lake Shoreline

The spatiotemporal object increments within lake shorelines reveal the locations of changes and provide insights into the nature of these alterations. Additionally, the specific evolution directions corresponding to diverse shoreline evolution modes can elucidate the directional trends of lake “expansion” or “shrinkage” at a patch scale. The introduction of new lake units is expressed through “target positive difference”, while the disappearance of lakes is depicted by “shrinkage negative difference”. Neither of these inherently addresses the aspect of directionality within their evolution.

Therefore, in this study, we focused on the evolution direction concerning the “positive difference of expansion” and “negative difference of contraction” within lake shorelines. To measure the evolution direction of lake units, we employed the following approach. First, the lake patches that have undergone a “positive difference of expansion” or “negative difference of contraction” were extracted. Second, the common edge between these patches and the previous year’s lake shoreline was identified. Third, the common edge between the patches and the current annual lake shoreline was identified. Fourth, the midpoint of the aforementioned two shared edges was extracted. Finally, according to the coordinates of the respective midpoints, the evolution direction of the “positive difference of expansion” or “negative difference of contraction” was computed (Figure 2).

3.4. Analysis Method of Spatiotemporal Characteristics of Lake Shoreline Evolution

The analysis of the spatiotemporal characteristics of lake shoreline evolution benefits from long-term remote sensing data. The size of the areas undergoing “expansion”, “shrinkage”, “appearance”, and “disappearance” along the lake shoreline in consecutive years is a fundamental feature in the spatiotemporal evolution of the shoreline. Therefore, in this study, the year-to-year changes in the area for each of the aforementioned four evolution patterns were quantified, and a graph that offers an intuitive and quantitative insight into the changing trends of the study area was constructed. Additionally, the frequency distribution of lake patches involved in each evolution pattern at different intervals is another essential feature of the coastline evolution process.

Our procedure encompassed multiple steps. Initially, we divided the shoreline’s evolution direction into 16 intervals. Subsequently, we extracted patches corresponding to the “expansion” and “shrinkage” of the lake shoreline over the past two decades. We then calculated the frequency of evolution directions for various patches falling within each of the 16 direction intervals. Finally, we graphically depicted the general characteristics of lake shoreline “expansion” or “shrinkage”.

Clustering is a technique used to identify similarities among objects in a dataset, after which the objects are grouped into clusters according to these similarities. By employing cluster analysis on the evolution of lake shorelines, we can reveal potential clusters exhibiting similar evolution traits. In our study, we treated every two consecutive years as an instance and defined the “expansion”, “shrinkage”, “appearance”, and “disappearance” during that period as the eigenvector for that instance. Subsequently, cluster analysis was conducted on these instances through various clustering methods. A K-means algorithm was used, and the appropriate k value was selected via the elbow (elbow coefficient) method.

4. Results and Discussion

Gaining an understanding of the changes in the water level and land use of Shengjin Lake is crucial for comprehending the geographical context behind the evolution of the lake’s shoreline. In recent years, extreme weather events have become more frequent owing to global climate change. Precipitation in the Shengjin Lake area has also significantly increased over the years, resulting in a notable historical highwater level of 17.5 m on 10 July 2016. This paper presents the average water level of Shengjin Lake during the flood season from July to September (Figure 3 and Figure 4). Considering that the water level of Shengjin Lake has been recorded since 2003, the graph’s start and end years were set to 2003, differing from the remote sensing images presented in this study that cover the period since 2001. The average water level graph shows that Shengjin Lake’s water level has risen considerably over time. Except for just two years (2006 and 2018) marked by significant low-water levels, the overall trend illustrates a general increase in Shengjin Lake’s water level. Remarkably, in 2020, the lake’s water level exhibited a marked rise, reaching a notably high point.

To gain a comprehensive understanding of the relationship between water level and shoreline, an analysis was conducted to determine the correlations between water level and shoreline length and lake area. The corresponding R² values were 0.41 and 0.69, respectively, indicating a relatively weak correlation between water level and shoreline length and a moderately stronger correlation with lake area. Thus, water level might not be the predominant factor influencing the evolutionary patterns of “expansion”, “contraction”, “appearance”, or “disappearance” in Shengjin Lake’s shoreline. The diverse terrain surrounding Shengjin Lake, characterized by extensive, sinuous shores and numerous lakes, could be a primary contributing factor to this phenomenon.

4.1. Time Series Characteristics of Different Coastline Evolution Patterns

This study utilized a 20-year series of remote sensing images of the Shengjin Lake wetland to generate a total of 19 temporal and spatial snapshot difference datasets. Each space–time snapshot difference dataset encompassed data that reflected various evolution modes, such as “expansion”, “shrinkage”, “appearance”, and “disappearance”.

Over the past 20 years, the area of Shengjin Lake’s shoreline has displayed significant fluctuations. Some years have witnessed substantial expansion, such as from 2001 to 2002, 2006 to 2007, 2010 to 2011, and 2019 to 2020, while other years have experienced only minor expansion, such as from 2016 to 2018. In comparison, the range of fluctuation for “shrinkage” has been small. The area’s “shrinkage” has remained below 30 km², and in most years, it has been below 20 km². Figure 4 illustrates a clear negative correlation between the “expansion” and “shrinkage” of the lake shoreline. From 2003 to 2004, 2012 to 2013, and 2013 to 2014, both the “expansion” and “shrinkage” areas of the lake shoreline exhibited minimal variation. In other interannual periods, the lake shoreline exhibited either “expansion” or “shrinkage”.

Figure 5 illustrates that the range of area changes for “appearance” and “disappearance” along the shoreline of Shengjin Lake have remained relatively small (<2.5 km²) over the past 20 years. The interannual variability within this range is considerably smaller compared with those of “expansion” and “shrinkage”. This implies that the dominant evolution modes of the Shengjin Lake wetland are primarily characterized by “expansion” and “shrinkage”, possibly owing to the region’s terrain. The relatively flat topography and absence of significant undulations are unsuitable for the formation of minor watersheds. Furthermore, no distinct positive or negative correlation was observed between the “appearance” and “disappearance” of the Shengjin Lake wetland. For instance, during the periods of 2001–2002, 2006–2007, 2013–2014, and 2015–2016, the total area covered by “appearance” water units was larger than that covered by “disappearance” water units. However, in instances such as 2007 to 2008 and 2011 to 2012, the total areas of “appearance” and “disappearing” water units were quite similar.

Different evolution types exhibited significant variations in the size and number of involved evolutionary units. The analysis of Shengjin Lake’s shoreline evolution process over the past two decades demonstrated distinct differences in the number of evolutionary units engaged in various evolution patterns. Over the 20-year span, 2725 patches underwent expansion, 3059 experienced contraction, 198 new patches emerged, and 177 patches disappeared (Figure 6). “Expansion” and “shrinkage” encompassed numerous evolutionary units, but the area of each unit was relatively small, with most measuring less than 0.1 km² (Figure 6). In contrast, “appearance” and “disappearance” involved a small number of evolutionary units, and their area distribution followed a “bell” curve similar to a Gaussian model. The areas of these evolutionary units predominantly fell between 0.01 and 0.1 km² (Figure 7).

4.2. Analysis of Orientation Characteristics of Different Lake Shoreline Evolution Patterns

The temporal characteristics of shoreline evolution direction can provide insights into the overall trend of Shengjin Lake’s shoreline evolution. Therefore, through statistical analysis of the evolutionary directions, the total frequency of changes in the “expansion” and “contraction” directions over the past 20 years was determined (Figure 8). The primary direction of “expansion” was toward the northeast, while “shrinkage” predominantly occurred toward the southwest. The last two decades have exhibited significant directional distinctions between the “expansion” and “shrinkage” patterns of Shengjin Lake’s shoreline. However, incorporating additional data is crucial to fully elucidate the underlying factors contributing to these differences. According to the results of the third national land resource survey conducted by the Chinese government, wetland grasslands are primarily situated in the northeast and southwest areas surrounding Shengjin Lake. These regions possess fragile ecological environments that are susceptible to the impacts of human activities and climate change, rendering them prone to ecological risks. Consequently, these specific segments of the lake are characterized by frequent large-scale expansion and contraction.

4.3. Cluster Analysis of Different Shoreline Evolution Patterns

K-means-based cluster analysis was conducted on the sequence data of the 19 temporal snapshots. The results revealed that the shoreline evolution process during these 19 periods can be classified into two distinctive clusters. The first cluster, designated as A, encompassed 2001–2002, 2002–2003, 2006–2007, 2009–2010, 2010–2011, 2012–2013, 2014–2015, 2015–2016, 2018–2019, and 2019–2020. Conversely, the second cluster, designated as B, encompassed 2003–2004, 2004–2005, 2005–2006, 2007–2008, 2008–2009, 2011–2012, 2013–2014, 2016–2017, and 2017–2018. Alterations in Class A’s shoreline were relatively gradual, while Class B exhibited more pronounced changes (Figure 9). In Figure 9, the solid square represents the extreme outliers of area normalization value in the change process of the long-term evolution charcateristice of lake shorelines, while the hollow square represents the average value of the area normalization value. From 2003 to 2010, the Shengjin Lake wetland witnessed significant expansion of aquaculture within the enclosed area and intense human intervention, leading to a phase of rapid growth. This phase corresponds to Class B, characterized by dramatic changes. For cases of both “expansion” and “shrinkage”, the variations in Class A were significantly smaller than those in Class B. Additionally, in Class B, the range of change for “expansion” was considerably broader than that for “shrinkage”.

5. Conclusions

An analysis of Shengjin Lake’s shoreline evolution patterns over the past two decades reveals that the changing area of the lake shoreline has exhibited significant fluctuations, primarily characterized by the evolutionary modes of “expansion” and “shrinkage”. The overarching trend of Shengjin Lake wetland’s evolution is predominantly defined by these modes, with no evident correlation observed between the “appearance” and “disappearance” of the shoreline. The principal evolutionary direction for “expansion” is northeastward, while “shrinkage” predominantly occurs in the southwest direction, potentially influenced by human activities and climate change. Additionally, the shoreline evolution patterns can be classified into two categories, with Class B undergoing more pronounced changes than Class A. These findings underscore the fragile ecological environment surrounding Shengjin Lake, which is susceptible to the impacts of human activities and climate variations, thus emphasizing the necessity of effective management and conservation strategies to safeguard this vital ecosystem.

This paper discusses the extraction methods of four typical lake shoreline evolution patterns—namely “expansion”, “contraction”, “appearance”, and “disappearance”—from the perspective of the spatiotemporal semantics of lake shoreline evolution. Furthermore, the spatiotemporal disparities among the four lake shoreline evolution modes are quantitatively analyzed. However, changes in lake shorelines can arise from numerous factors, and a preliminary analysis based on factors such as water level and land use and land cover type was conducted. Nonetheless, these analyses did not fully reveal the primary drivers behind the evolution of shorelines in the study area. In subsequent research, additional data will be gathered and integrated with lake topography, precipitation patterns, and other pertinent information to comprehensively analyze the shoreline evolution process of lakes. This comprehensive approach aims to provide valuable insights for lake shoreline management and wetland conservation efforts.