**3.1 Earthwork optimizer**

The earthwork optimizer in *GoogleEarthWork* (**Figure 6**) models site constraints and earthwork operations with a flow network model. Those quantitative constraints are defined as attributes associated with nodes, while qualitative constraints are represented in the network structure as follow: To establish such a model, the construction site is first divided into cells. For simplicity, the site can be divided into regular square cells. The links between cells can be derived directly by connecting a

**143**

respectively:

**Figure 6.**

*system.*

∑

*Google Earth Augmented for Earthwork Construction Planning*

cell with its neighbor cells sharing four common edges. The division of the site into cells needs to consider the design, the site layout, elevation changes, and accesses. For example, defining separate cells at a specific position is preferred if abrupt elevation change occurs, thus resulting in definition of irregular cells. Occasionally, treating a particular site area as one node is preferable if it has limited access. In short, the identification of these problems requires integration of information on design, actual construction site, and the surrounding environment. Once the site has been digitized into a cell model, the next step is to establish the flow network

*Flow network model for earthwork optimization and state presentation in GoogleEarthWork. (a) Typical constraints on a construction site, (b) quantitative constraints and qualitative constraints modeled as attributes and network structure, respectively, and (c) optimized earth flow network used to represent the state of the* 

Prior to delving into the core of the earthwork optimizer in *GoogleEarthWork*, several important concepts need to be clarified. A *graph model G* = (*V*,*E*) is made of a set of vertices *V* and a set of edges *E* which defines the connectivity between the vertices.

vertex *v* ∈ *V* is defined as (*u*,*v*). For a *directed graph*, edge (*u*,*v*) and edge (*v*,*u*) represent reversed directions. A flow network is defined as follows based on the *directed graph*: A *flow network* is a directed graph, where each vertex is assigned with a demand *d*(*v*) and each edge (*u*,*v*) is assigned with a capacity *cuv* > 0, a unit cost *auv*, and a flow *xuv*. The demand is the amount of flow that is required by this vertex. If *<sup>d</sup>* <sup>&</sup>gt; 0, the vertex is demanding material to flow in. It is also called a sink node. On the contrary, it is a supplying vertex also named as source node if *d* < 0. Otherwise, the vertex will be a transshipment node with *d* = 0. The capacity *cuv* indicates the maximum flow allowed on each edge. The cost *auv* is the unit cost to transport each flow unit through individual edges, respectively. The flow*xuv* specifies the amount of flow on each edge.

(*u*,*v*)∈*E*

0 ≤ *xuv* ≤ *cuv* for all (*u*, *v*) ∈ *E* (2)

where **x** = {*xuv*|(*u*, *v*) ∈ *E*} represents the flow variables indicating the amount of flow on an edge. The optimal flow **x**min can be found by applying the minimum-cost flow algorithms [58] which minimize the cost function defined in Eq. (2) subject to capacity constraints and balance constraints defined in Eq. (3) and Eq. (4),

,⋯ ,*vn*}, an edge between vertex *u* ∈ *V* and

*auvxuv* (1)

*xvw* = *dv* for all *v* ∈ *N* (3)

model incorporating various quantitative and qualitative constraints.

Given a list of vertices *V* = {*v*1,*v*2,⋯ ,*vi*,⋯ ,*vj*

The total cost of a flow network is defined as:

(*u*,*v*)∈*E*

*xuv* − ∑ (*v*,*w*)∈*E*

*h*(**x**) = ∑

*DOI: http://dx.doi.org/10.5772/intechopen.82008*

**Figure 5.**

*Scheme for embedding automated earthwork planning system in GoogleEarthWork.*

*Google Earth Augmented for Earthwork Construction Planning DOI: http://dx.doi.org/10.5772/intechopen.82008*

**Figure 6.**

*Geographic Information Systems and Science*

models in reality.

**3.1 Earthwork optimizer**

as temporal-spatial conflicts in field operations would result in overcomplicated mathematical models which had reduced application values of the developed

The architecture of the two-phase approach is illustrated in **Figure 5**. At the bottom, an earthwork optimizer based on a material flow network is developed to optimize earthwork operations subject to identified quantitative and qualitative constraints. The optimization result is then taken as the primary input for ensuing analysis by the earthwork planner, which generates haul jobs, defines inter-job relationships, and produces the project network model for project scheduling and control.

The earthwork optimizer in *GoogleEarthWork* (**Figure 6**) models site constraints

and earthwork operations with a flow network model. Those quantitative constraints are defined as attributes associated with nodes, while qualitative constraints are represented in the network structure as follow: To establish such a model, the construction site is first divided into cells. For simplicity, the site can be divided into regular square cells. The links between cells can be derived directly by connecting a

**142**

**Figure 5.**

*Scheme for embedding automated earthwork planning system in GoogleEarthWork.*

*Flow network model for earthwork optimization and state presentation in GoogleEarthWork. (a) Typical constraints on a construction site, (b) quantitative constraints and qualitative constraints modeled as attributes and network structure, respectively, and (c) optimized earth flow network used to represent the state of the system.*

cell with its neighbor cells sharing four common edges. The division of the site into cells needs to consider the design, the site layout, elevation changes, and accesses. For example, defining separate cells at a specific position is preferred if abrupt elevation change occurs, thus resulting in definition of irregular cells. Occasionally, treating a particular site area as one node is preferable if it has limited access. In short, the identification of these problems requires integration of information on design, actual construction site, and the surrounding environment. Once the site has been digitized into a cell model, the next step is to establish the flow network model incorporating various quantitative and qualitative constraints.

Prior to delving into the core of the earthwork optimizer in *GoogleEarthWork*, several important concepts need to be clarified. A *graph model G* = (*V*,*E*) is made of a set of vertices *V* and a set of edges *E* which defines the connectivity between the vertices. Given a list of vertices *V* = {*v*1,*v*2,⋯ ,*vi*,⋯ ,*vj* ,⋯ ,*vn*}, an edge between vertex *u* ∈ *V* and vertex *v* ∈ *V* is defined as (*u*,*v*). For a *directed graph*, edge (*u*,*v*) and edge (*v*,*u*) represent reversed directions. A flow network is defined as follows based on the *directed graph*:

A *flow network* is a directed graph, where each vertex is assigned with a demand *d*(*v*) and each edge (*u*,*v*) is assigned with a capacity *cuv* > 0, a unit cost *auv*, and a flow *xuv*.

The demand is the amount of flow that is required by this vertex. If *<sup>d</sup>* <sup>&</sup>gt; 0, the vertex is demanding material to flow in. It is also called a sink node. On the contrary, it is a supplying vertex also named as source node if *d* < 0. Otherwise, the vertex will be a transshipment node with *d* = 0. The capacity *cuv* indicates the maximum flow allowed on each edge. The cost *auv* is the unit cost to transport each flow unit through individual edges, respectively. The flow*xuv* specifies the amount of flow on each edge.

The total cost of a flow network is defined as:

$$h\left(\mathbf{x}\right) = \sum\_{(u,v)\in E} a\_{uv}\mathbf{x}\_{uv} \tag{1}$$

where **x** = {*xuv*|(*u*, *v*) ∈ *E*} represents the flow variables indicating the amount of flow on an edge. The optimal flow **x**min can be found by applying the minimum-cost flow algorithms [58] which minimize the cost function defined in Eq. (2) subject to capacity constraints and balance constraints defined in Eq. (3) and Eq. (4), respectively:

$$0 \le \varkappa\_{uv} \le c\_{uv} \quad \text{for all } (u,v) \in E \tag{2}$$

$$\sum\_{(u,v)\in E} \mathcal{X}\_{uv} - \sum\_{(v,w)\in E} \mathcal{X}\_{vw} = d\_v \quad \text{for all } v \in N \tag{3}$$

Traditional methods model haul jobs directly by adding links only between cut and fill cells. These methods require predefined hauling paths which may not be explicitly specified in earthwork planning, as hauling paths can be included as variables to be optimized in addition to earth volume assignment variables between cut and fill cells. In [56], a new method is introduced to deal with the issue without increasing the complexity of problem formulation. In contrast to linking cut cells to fill cells directly, this method links neighbor cells irrespective of whether they are cut or fill cells, while the exact hauling path for each haul job will be fixed by optimization along with the source cell (cut), the destination cell (fill), and the volume to handle for each haul job.

The quantitative constraints such as cut/fill volumes and the traveling speed are directly modeled as the demand *dv* for each node and the unit cost *auv* for each edge, respectively. The capacity of flow on an edge is typically unlimited unless there is a special need, for example, to limit the total amount moved to a storage area. The qualitative constraints are modeled implicitly in the network structure. They are embedded by adding or removing specific arcs at specific directions. In the following subsections, we will elaborate typical site constraints for earthwork including accessibility, reserved areas, and haul road conditions.

**Accessibility constraints:** Site accessibility constraints are the most common on a construction site. The access between cells may be blocked by waterways, ponds, other facilities, and so on. Prohibiting moving material from one cell to another may be justified in certain areas in order to ensure traffic safety and provide adequate space for other construction activities. This can be imposed by removing certain directional arcs between cells in the site grid model in order to moderate earth flows.

**Reserved area constraints:** Reserved areas for temporary facilities, such as fuel stations, parking yards, and rest areas, require grading as well, but trucks generally are not allowed to pass through these areas once the temporary facilities are established. They can be treated as special cases of accessibility constraints. Taking the example presented in **Figure 8**, the site is divided into regular cells. Among them, cell 3 and cell 5 cover the area where a structure is being built. After the excavation in this area, there will be a substantial elevation change. Passing through this area is thus not allowed. Considering this area is a net cut area (the total demand is negative); only material flows leaving this area (red dash rectangle) are permitted. Similarly, only material flows entering an area are allowed if this area is a net fill area.

**Haul road condition constraints:** It is noteworthy that the truck hauling speed on rough ground and treated ground varies significantly. In the flow network model, haul road conditions can be modeled by adjusting the unit cost *auv* of particular edges which represent haul road sections in the flow network. Shortening total project duration is the objective in construction planning in general. Thus, the traveling time can be used to directly model the cost.

Once the model is established, it is optimized with established minimum-cost flow algorithms [59]. As a result, the earthwork optimizer produces a flow network that defines the amount of flows (defined by **x**) between adjacent cells. Because it does not model haul jobs directly, the result cannot produce the final execution plan which defines each haul job in terms of source, destination, volume, and haul path. Next, the earthwork planner is introduced which generates the final execution plan based on the optimized earth flow network.

#### **3.2 Earthwork planner**

The optimized earth flow network specifies quantity and direction to move material along inter-cell edges (haul roads) in the site system. However, temporal or spatial constraints arising from sequencing earthmoving jobs can be missed in this

**145**

**Figure 7.**

*a haul job generation model.*

*Google Earth Augmented for Earthwork Construction Planning*

and the network to represent the accessibility is named as *Gac*.

representation. At the beginning of earthwork operations, only limited accessibility is available. Access to an area is enabled in the middle of the earthmoving process once its neighbor areas are graded. Thus an additional network is required to define the accessibility between areas considering the progress of the project over time. In the remainder of this chapter, the optimized earth flow network is denoted as *Gop*,

In this step, the classical planning model in automated planning theory is adopted for earthwork project planning in *GoogleEarthWork*. The state transition system for the earthwork planner is defined with a triple ∑= (**S**,,), where.

**S** is defined with a tuple of two directed graphs (*Gac*,*Gop*), where *Gop* is the optimal earth flow network and *Gac* is a directed graph representing the accessibility

 is the action space defined as haul jobs. Each haul job can be represented with (*WF* = (*Cut*,*Fill*),*P*,*V*) which specifies the cut and fill cells, together with the volume V and the hauling path P. For example, a haul job (*WF* <sup>=</sup> (*Cut*,*Fill*),*P*,*V*) indicates 20 units of material which are transported from Cell 1 to Cell 2 passing through Cell 3 and Cell 4. *y* is a map from *S* × *A* to *S* where the optimal earth flow network and the accessibility are updated after performing an action (i.e., completing a haul job.) This

In the classical planning model, actions are sequentially taken by selecting an action and updating the state as presented in **Figure 7**. The procedure consists of four steps with the first three steps corresponding to deliberation functions and the

*The procedure of the earthwork planner. The deliberation functions include a cut/fill cell selection module and* 

*DOI: http://dx.doi.org/10.5772/intechopen.82008*

between cells.

includes the following:

(1) Updating the volumes of each cell on *Gop*

(2) Updating the flow between adjacent cells on *Gac*

(3) Updating accessibility on *Gac* after some cells are graded

*Google Earth Augmented for Earthwork Construction Planning DOI: http://dx.doi.org/10.5772/intechopen.82008*

*Geographic Information Systems and Science*

volume to handle for each haul job.

accessibility, reserved areas, and haul road conditions.

traveling time can be used to directly model the cost.

based on the optimized earth flow network.

**3.2 Earthwork planner**

Traditional methods model haul jobs directly by adding links only between cut and fill cells. These methods require predefined hauling paths which may not be explicitly specified in earthwork planning, as hauling paths can be included as variables to be optimized in addition to earth volume assignment variables between cut and fill cells. In [56], a new method is introduced to deal with the issue without increasing the complexity of problem formulation. In contrast to linking cut cells to fill cells directly, this method links neighbor cells irrespective of whether they are cut or fill cells, while the exact hauling path for each haul job will be fixed by optimization along with the source cell (cut), the destination cell (fill), and the

The quantitative constraints such as cut/fill volumes and the traveling speed are directly modeled as the demand *dv* for each node and the unit cost *auv* for each edge, respectively. The capacity of flow on an edge is typically unlimited unless there is a special need, for example, to limit the total amount moved to a storage area. The qualitative constraints are modeled implicitly in the network structure. They are embedded by adding or removing specific arcs at specific directions. In the following subsections, we will elaborate typical site constraints for earthwork including

**Accessibility constraints:** Site accessibility constraints are the most common on a construction site. The access between cells may be blocked by waterways, ponds, other facilities, and so on. Prohibiting moving material from one cell to another may be justified in certain areas in order to ensure traffic safety and provide adequate space for other construction activities. This can be imposed by removing certain directional arcs between cells in the site grid model in order to moderate earth flows. **Reserved area constraints:** Reserved areas for temporary facilities, such as fuel stations, parking yards, and rest areas, require grading as well, but trucks generally are not allowed to pass through these areas once the temporary facilities are established. They can be treated as special cases of accessibility constraints. Taking the example presented in **Figure 8**, the site is divided into regular cells. Among them, cell 3 and cell 5 cover the area where a structure is being built. After the excavation in this area, there will be a substantial elevation change. Passing through this area is thus not allowed. Considering this area is a net cut area (the total demand is negative); only material flows leaving this area (red dash rectangle) are permitted. Similarly, only material flows entering an area are allowed if this area is a net fill area. **Haul road condition constraints:** It is noteworthy that the truck hauling speed

on rough ground and treated ground varies significantly. In the flow network model, haul road conditions can be modeled by adjusting the unit cost *auv* of

particular edges which represent haul road sections in the flow network. Shortening total project duration is the objective in construction planning in general. Thus, the

Once the model is established, it is optimized with established minimum-cost flow algorithms [59]. As a result, the earthwork optimizer produces a flow network that defines the amount of flows (defined by **x**) between adjacent cells. Because it does not model haul jobs directly, the result cannot produce the final execution plan which defines each haul job in terms of source, destination, volume, and haul path. Next, the earthwork planner is introduced which generates the final execution plan

The optimized earth flow network specifies quantity and direction to move material along inter-cell edges (haul roads) in the site system. However, temporal or spatial constraints arising from sequencing earthmoving jobs can be missed in this

**144**

representation. At the beginning of earthwork operations, only limited accessibility is available. Access to an area is enabled in the middle of the earthmoving process once its neighbor areas are graded. Thus an additional network is required to define the accessibility between areas considering the progress of the project over time. In the remainder of this chapter, the optimized earth flow network is denoted as *Gop*, and the network to represent the accessibility is named as *Gac*.

In this step, the classical planning model in automated planning theory is adopted for earthwork project planning in *GoogleEarthWork*. The state transition system for the earthwork planner is defined with a triple ∑= (**S**,,), where.

**S** is defined with a tuple of two directed graphs (*Gac*,*Gop*), where *Gop* is the optimal earth flow network and *Gac* is a directed graph representing the accessibility between cells.

 is the action space defined as haul jobs. Each haul job can be represented with (*WF* = (*Cut*,*Fill*),*P*,*V*) which specifies the cut and fill cells, together with the volume V and the hauling path P. For example, a haul job (*WF* <sup>=</sup> (*Cut*,*Fill*),*P*,*V*) indicates 20 units of material which are transported from Cell 1 to Cell 2 passing through Cell 3 and Cell 4.

*y* is a map from *S* × *A* to *S* where the optimal earth flow network and the accessibility are updated after performing an action (i.e., completing a haul job.) This includes the following:

(1) Updating the volumes of each cell on *Gop*


In the classical planning model, actions are sequentially taken by selecting an action and updating the state as presented in **Figure 7**. The procedure consists of four steps with the first three steps corresponding to deliberation functions and the

#### **Figure 7.**

*The procedure of the earthwork planner. The deliberation functions include a cut/fill cell selection module and a haul job generation model.*

fourth step corresponding to state transition functions. Because actions are required to satisfy all material flow constraints (flow direction and flow quantity on each edge), which are already determined in the optimized flow network, the final plan is extracted from a searching space that is already optimized. The detailed explanation of the planner can be found in [56, 57].

## **4. Case study**

In this section a campground grading project located in Northern Alberta, Canada, is used to demonstrate the application of earthwork optimization and automated planner functions. The size of the campground is around 2000 m long and 650 m wide. The total volume of material to be handled is 584,308 bank cubic meters (*bcm*). The site layout is presented in **Figure 8** with color bands denoting deep excavation (>3 m), medium height excavation (1.5–3 m), shallow excavation (<1.5 m), shallow fill (<1.5 m), and medium-depth fill (1.5–3 m). On the west side and east side, respectively, there are two storm water storage ponds, which also provide the two primary sources for fill material in site grading. Note during construction, only limited access to the two ponds is allowed. Pond 1 has one access point on its east side; Pond 2 has two access points on its north and west sides, respectively.

A temporary haul road aligned with a future permanent road is established to facilitate the earthmoving process. Average truck speed differs when a truck hauls on the temporary road or the rough-graded ground. A fleet consisting of a 40 T excavator with a production rate of 190 *bcm* per day and CAT 740B trucks with 20 *bcm* volume capacity are employed on this project. The combined loading, dumping, and waiting time is assumed to be 20 minutes. The truck hauling speed limit, irrespective of truck haul (full) and truck return (empty), is averaged at 27 km/h on temporary haul road and 18 km/h on rough ground, respectively. Besides, hourly rates of the excavator and the truck are 140/*hr* and 135/*hr*. The hourly rate for an equipment operator is around 60/*hr* regardless of the type of the equipment.

The construction site is divided into cells (100 m × 100 m) for material flow network optimization and AON network development. The cell size is defined by the user after assessing site topology and application need. Mathematically, the smaller the cell size, the more accurate the result would be. However, too small cell size is not suitable for current application of earthwork planning and construction management. Four times the truck width is recommended as cell dimension for planning mining haul road, which was used for earthwork planning in *GoogleEarthWork* due to safety concerns [60]. To incorporate the two ponds in the flow network model, irregular shaped cells instead of squared cells are used for representing the ponds,

**147**

**5. Conclusion**

**Figure 9.**

*Google Earth Augmented for Earthwork Construction Planning*

*Flow network model for the case study. Two ponds are split into irregular cells.*

their neighboring areas, and the boundaries. In this case, Pond 1 is treated as one cell node, and Pond 2 is divided into two cell nodes. Single-directional arcs flowing out of pond cells are defined so to avoid trucks passing through the ponds. The traveling time per truckload between adjacent cells is defined as the unit cost of hauling in optimization analysis. The final flow network definition is presented in **Figure 9**. The *earthwork Optimizer* and the *earthwork Planner* in connection with *GoogleEarthWork* were implemented based on the open source Library for Efficient Modeling and Optimization in Networks (LEMON) graph algorithm library with its LGF file format denoting flow network definition [61]. Taking the flow network model as input, an optimized earth flow network was obtained as the result of minimum-cost flow optimization. Next, eight sub-flows were identified from the optimized earth flow network based on weakly connected component analysis. In the end, a total of 129 jobs were generated. The proposed system not only enables automated project planning but also automated project network analysis and

resource-loaded scheduling simulation analysis. Once the work breakdown structure and the project network are produced, they can be readily used to perform scheduling and cost analysis with existing tools. Based on the automated planner, the cost and duration were estimated to be \$3,491,632 and 149 work days, respectively.

In this chapter, we conceptualize an augmented GIS system called

*GoogleEarthWork* for earthwork planning based on Google Earth and demonstrate great potential in site information management and visualization, especially the integration of site photos, 3D models, and 3D surrounding environment of the construction site. The system is capable of facilitating the identification of (1) quantitative constraints by image-based 3D reconstruction and (2) qualitative constraints through interactive VR and AR visual inspection within Google Earth. Coupled with an automated earthwork planning system, *GoogleEarthWork* holds the potential to provide an integrated project planning solution that assists project managers in information collection, data analysis, and construction planning. It also enables higher-level project management analyses such as scheduling and simulation by automatically generating project execution plans (e.g., AON network model). The results provide project managers with a sufficient basis for the development of a practical, dynamic plan. As construction unfolds and the site evolves over time, additional constraints can be further imposed in order to keep the plan up to date. At present, application of *GoogleEarthWork* is confined to rough grading earthwork construction. In the future, the system along with its underlying methodology

*DOI: http://dx.doi.org/10.5772/intechopen.82008*

**Figure 8.** *Rough grading construction site: drawing and layouts.*

*Google Earth Augmented for Earthwork Construction Planning DOI: http://dx.doi.org/10.5772/intechopen.82008*

*Geographic Information Systems and Science*

tion of the planner can be found in [56, 57].

**4. Case study**

fourth step corresponding to state transition functions. Because actions are required to satisfy all material flow constraints (flow direction and flow quantity on each edge), which are already determined in the optimized flow network, the final plan is extracted from a searching space that is already optimized. The detailed explana-

In this section a campground grading project located in Northern Alberta, Canada, is used to demonstrate the application of earthwork optimization and automated planner functions. The size of the campground is around 2000 m long and 650 m wide. The total volume of material to be handled is 584,308 bank cubic meters (*bcm*). The site layout is presented in **Figure 8** with color bands denoting deep excavation (>3 m), medium height excavation (1.5–3 m), shallow excavation (<1.5 m), shallow fill (<1.5 m), and medium-depth fill (1.5–3 m). On the west side and east side, respectively, there are two storm water storage ponds, which also provide the two primary sources for fill material in site grading. Note during construction, only limited access to the two ponds is allowed. Pond 1 has one access point on its east side; Pond 2 has two access points on its north and west sides, respectively. A temporary haul road aligned with a future permanent road is established to facilitate the earthmoving process. Average truck speed differs when a truck hauls on the temporary road or the rough-graded ground. A fleet consisting of a 40 T excavator with a production rate of 190 *bcm* per day and CAT 740B trucks with 20 *bcm* volume capacity are employed on this project. The combined loading, dumping, and waiting time is assumed to be 20 minutes. The truck hauling speed limit, irrespective of truck haul (full) and truck return (empty), is averaged at 27 km/h on temporary haul road and 18 km/h on rough ground, respectively. Besides, hourly rates of the excavator and the truck are 140/*hr* and 135/*hr*. The hourly rate for an equipment

operator is around 60/*hr* regardless of the type of the equipment.

The construction site is divided into cells (100 m × 100 m) for material flow network optimization and AON network development. The cell size is defined by the user after assessing site topology and application need. Mathematically, the smaller the cell size, the more accurate the result would be. However, too small cell size is not suitable for current application of earthwork planning and construction management. Four times the truck width is recommended as cell dimension for planning mining haul road, which was used for earthwork planning in *GoogleEarthWork* due to safety concerns [60]. To incorporate the two ponds in the flow network model, irregular shaped cells instead of squared cells are used for representing the ponds,

**146**

**Figure 8.**

*Rough grading construction site: drawing and layouts.*

**Figure 9.** *Flow network model for the case study. Two ponds are split into irregular cells.*

their neighboring areas, and the boundaries. In this case, Pond 1 is treated as one cell node, and Pond 2 is divided into two cell nodes. Single-directional arcs flowing out of pond cells are defined so to avoid trucks passing through the ponds. The traveling time per truckload between adjacent cells is defined as the unit cost of hauling in optimization analysis. The final flow network definition is presented in **Figure 9**.

The *earthwork Optimizer* and the *earthwork Planner* in connection with *GoogleEarthWork* were implemented based on the open source Library for Efficient Modeling and Optimization in Networks (LEMON) graph algorithm library with its LGF file format denoting flow network definition [61]. Taking the flow network model as input, an optimized earth flow network was obtained as the result of minimum-cost flow optimization. Next, eight sub-flows were identified from the optimized earth flow network based on weakly connected component analysis. In the end, a total of 129 jobs were generated. The proposed system not only enables automated project planning but also automated project network analysis and resource-loaded scheduling simulation analysis. Once the work breakdown structure and the project network are produced, they can be readily used to perform scheduling and cost analysis with existing tools. Based on the automated planner, the cost and duration were estimated to be \$3,491,632 and 149 work days, respectively.
