A multilevel ACO approach for solving forest transportation planning problems with environmental constraints

Lin, Pengpeng; Contreras, Marco A.; Dai, Ruxin; Zhang, Jun

doi:10.1016/j.swevo.2016.01.003

Cited by 10 publications

(6 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The need to address road management issues in spatial and temporal context at a large scale has been increasing as social and environmental demands and concerns increase around forest resources management. [26] ACOLS has certainly the potential to provide a useful and efficient tool to meet such needs.…”

Section: Discussionmentioning

confidence: 99%

Combining ant colony optimization with 1-opt local search method for solving constrained forest transportation planning problems

Lin

Dai

Contreras

et al. 2017

AIR

Self Cite

View full text Add to dashboard Cite

We developed a two-stage approach (ACOLS) combining the ant colony optimization (ACO) algorithm and a 1-opt local search to solve forest transportation planning problems (FTPPs) considering fixed and variables costs and sediment yields expected to erode from road surfaces as side constraints. The ACOLS was designed for improving ACO performance and ensure the applicability to real-world, large-scale FTPPs with multiple time periods. It consists of three major routines: i) least-cost route finding process from all timber sales simultaneously, ii) two stage search process developed to quickly find feasible (stage I) and high-quality (stage II) solutions and, iii) 1-opt local search solution refinement to further improve solution quality. The ACOLS was first applied to a medium-scale hypothetical FTPP on which four cases with increasing level of sediment constraint were considered. To test for robustness, the ACOLS was then applied to ten different problems instances created basing on the same topology of the hypothetical FTPP. Lastly, the ACOLS was applied to a real-world, large-scale FTPP considering thousands of roads segments, hundreds of timber sales, and multiple products and planning periods. Feasible solutions were found for all cases indicating the usefulness of our approach to provide managers with an efficient tool to address large-scale transportation problems.

show abstract

Section: Discussionmentioning

confidence: 99%

Combining ant colony optimization with 1-opt local search method for solving constrained forest transportation planning problems

Lin

Dai

Contreras

et al. 2017

AIR

Self Cite

View full text Add to dashboard Cite

show abstract

“…Ants travel a path in order to find food and they leave a material known as pheromone proportional to the length of path and quality of nutrients. Other ants smell pheromone and travel the same path and therefore the value of pheromone is amplified; this way, the paths that have shorter length from nest to food source have higher amount of pheromone and are selected as optimal paths (Lin et al, 2016).…”

Section: Ant Colony (Aco)mentioning

confidence: 99%

An automatic visible-range video weed detection, segmentation and classification prototype in potato field

Sabzi

Abbaspour‐Gilandeh

Arribas

2020

Heliyon

View full text Add to dashboard Cite

Weeds might be defined as destructive plants that grow and compete with agricultural crops in order to achieve water and nutrients. Uniform spray of herbicides is nowadays a common cause in crops poisoning, environment pollution and high cost of herbicide consumption. Site-specific spraying is a possible solution for the problems that occur with uniform spray in fields. For this reason, a machine vision prototype is proposed in this study based on video processing and meta-heuristic classifiers for online identification and classification of Marfona potato plant (Solanum tuberosum) and 4299 samples from five weed plant varieties: Malva neglecta (mallow), Portulaca oleracea (purslane), Chenopodium album L (lamb's quarters), Secale cereale L (rye) and Xanthium strumarium (coklebur). In order to properly train the machine vision system, various videos taken from two Marfona potato fields within a surface of six hectares are used. After extraction of texture features based on the gray level cooccurrence matrix (GLCM), color features, spectral descriptors of texture, moment invariants and shape features, six effective discriminant features were selected: the standard deviation of saturation (S) component in HSV color space, difference of first and seventh moment invariants, mean value of hue component (H) in HSI color space, area to length ratio, average blue-difference chrominance (Cb) component in YCbCr color space and standard deviation of in-phase (I) component in YIQ color space. Classification results show a high accuracy of 98% correct classification rate (CCR) over the test set, being able to properly identify potato plant from previously mentioned five different weed varieties. Finally, the machine vision prototype was tested in field under real conditions and was able to properly detect, segment and classify weed from potato plant at a speed of up to 0.15 m/s.

show abstract

“…Weintraub et al (1995) developed an interactive procedure to solver large-scale transportation problems in which linear programming (LP) models were solved using heuristic decision rules in order to obtain approximated solutions. Contreras et al, (2008) applied a meta-heuristic ant colony optimization (ACO) algorithm to solve forest transportation problems, which was later evolved to a multilevel ACO approach to incorporate environmental constraints to the problem (Lin et al 2016). Although these heuristic methods may be able to produce good quality, feasible solutions to large-scale forest planning problems in a relatively reasonable solution time, their benefit can be realized only when the problem is significantly large and complex that the MILP approach cannot deliver an exact solution within a reasonable amount of time.…”

Section: Introductionmentioning

confidence: 99%

Partitioning and solving large-scale tactical harvest scheduling problems for industrial plantation forests

2020

View full text Add to dashboard Cite

Spatially explicit, tactical forest planning is a necessary but challenging task in the management of plantation forests. It involves harvest scheduling and planning for road access and log transportation over time and space. This combinatorial problem can be formulated into the fixed-charge transportation problem (FCTP), in which the sum of fixed and variable costs is minimized while meeting harvest volume requirements and allowing necessary road maintenance and log hauling activities. The problem can be solved using general optimization methods such as mixed-integer linear programming (MILP), but the computational efficiency of the MILP-based approach quickly drops as the size and complexity of the problem increases. We developed a new optimization procedure that partitions the large planning problem into smaller subproblems. We applied a hybrid optimization approach using both MILP and heuristic rules to efficiently solve the large FCTP that otherwise may not be solvable using traditional methods. We applied our approach to an industrial plantation forest in Brazil. Our applications demonstrate the performance of the new optimization procedure and the benefit of solving large forest planning problems that integrate harvest scheduling with road access and transportation.

show abstract

A multilevel ACO approach for solving forest transportation planning problems with environmental constraints

Cited by 10 publications

References 25 publications

Combining ant colony optimization with 1-opt local search method for solving constrained forest transportation planning problems

Combining ant colony optimization with 1-opt local search method for solving constrained forest transportation planning problems

An automatic visible-range video weed detection, segmentation and classification prototype in potato field

Partitioning and solving large-scale tactical harvest scheduling problems for industrial plantation forests

Contact Info

Product

Resources

About