Swarm intelligence for classification of remote sensing data

Liu, Xiaoping; Xia, Li; Peng, Xiaojuan; Li, Haibo; He, Jifeng

doi:10.1007/s11430-007-0133-6

Cited by 15 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our updating technique, we employed particle swarm optimization (PSO) due to its reliable global optimization capacities and flexibility in inputs and objective functions (see Section 2.2.3). PSO has seen various applications in remote sensing, frequently in image segmentation and classification [21][22][23], but also in agricultural applications. Guo et al, for example, used the algorithm to couple the PROSAIL canopy reflectance model with the WheatGrow crop model based on vegetation indices [24].…”

Section: Introductionmentioning

confidence: 99%

Remote Sensing Data Assimilation in Dynamic Crop Models Using Particle Swarm Optimization

Wagner

Slawig

Taravat

et al. 2020

IJGI

View full text Add to dashboard Cite

A growing world population, increasing prosperity in emerging countries, and shifts in energy and food demands necessitate a continuous increase in global agricultural production. Simultaneously, risks of extreme weather events and a slowing productivity growth in recent years has caused concerns about meeting the demands in the future. Crop monitoring and timely yield predictions are an important tool to mitigate risk and ensure food security. A common approach is to combine the temporal simulation of dynamic crop models with a geospatial component by assimilating remote sensing data. To ensure reliable assimilation, handling of uncertainties in both models and the assimilated input data is crucial. Here, we present a new approach for data assimilation using particle swarm optimization (PSO) in combination with statistical distance metrics that allow for flexible handling of model and input uncertainties. We explored the potential of the newly proposed method in a case study by assimilating canopy cover (CC) information, obtained from Sentinel-2 data, into the AquaCrop-OS model to improve winter wheat yield estimation on the pixel-and field-level and compared the performance with two other methods (simple updating and extended Kalman filter). Our results indicate that the performance of the new method is superior to simple updating and similar or better than the extended Kalman filter updating. Furthermore, it was particularly successful in reducing bias in yield estimation.

show abstract

Section: Introductionmentioning

confidence: 99%

Remote Sensing Data Assimilation in Dynamic Crop Models Using Particle Swarm Optimization

Wagner

Slawig

Taravat

et al. 2020

IJGI

View full text Add to dashboard Cite

show abstract

“…For PSO, a particle of swarm, denoting a candidate solution to the optimization problem, is initially assigned by a random position within the search space; the particle then strives to move towards the promising positions according to its own experience and the experience from neighbour particles, in other words, the particle updates positions by tracking its personal best position (pbest) and the global best position (gbest) memorized in each iteration (Masoomi et al 2013); by doing so, the whole swarm gradually moves to the promising areas, thus approaching (or achieving) the optimal solution in the end. Figure 1 illustrates the evolution process of a particle in a 2-D spatial space (Liu et al 2008). In the figure, ) (t X i and ) (t V i , respectively, denote the position and velocity of thei -th particle at time t , pbest i X and gbest X are the best positions found by the i -th particle and the whole swarm, respectively.…”

Section: Particle Swarm Optimizationmentioning

confidence: 99%

A novel unsupervised Levy flight particle swarm optimization (ULPSO) method for multispectral remote-sensing image classification

Zhang

et al. 2017

International Journal of Remote Sensing

View full text Add to dashboard Cite

“…In PSO, a candidate solution for a specific problem is called a particle. Each particle moves through the multi-dimensional problem space with a velocity that is dynamically adjusted by its own experience and those of its companions [ 36 ]. Finally, particles cooperate on exploring the problem space to find near-optimal solutions.…”

Section: Specification Of the Psola Modelmentioning

confidence: 99%

PSOLA: A Heuristic Land-Use Allocation Model Using Patch-Level Operations and Knowledge-Informed Rules

2016

View full text Add to dashboard Cite

Optimizing land-use allocation is important to regional sustainable development, as it promotes the social equality of public services, increases the economic benefits of land-use activities, and reduces the ecological risk of land-use planning. Most land-use optimization models allocate land-use using cell-level operations that fragment land-use patches. These models do not cooperate well with land-use planning knowledge, leading to irrational land-use patterns. This study focuses on building a heuristic land-use allocation model (PSOLA) using particle swarm optimization. The model allocates land-use with patch-level operations to avoid fragmentation. The patch-level operations include a patch-edge operator, a patch-size operator, and a patch-compactness operator that constrain the size and shape of land-use patches. The model is also integrated with knowledge-informed rules to provide auxiliary knowledge of land-use planning during optimization. The knowledge-informed rules consist of suitability, accessibility, land use policy, and stakeholders’ preference. To validate the PSOLA model, a case study was performed in Gaoqiao Town in Zhejiang Province, China. The results demonstrate that the PSOLA model outperforms a basic PSO (Particle Swarm Optimization) in the terms of the social, economic, ecological, and overall benefits by 3.60%, 7.10%, 1.53% and 4.06%, respectively, which confirms the effectiveness of our improvements. Furthermore, the model has an open architecture, enabling its extension as a generic tool to support decision making in land-use planning.

show abstract

Swarm intelligence for classification of remote sensing data

Cited by 15 publications

References 24 publications

Remote Sensing Data Assimilation in Dynamic Crop Models Using Particle Swarm Optimization

Remote Sensing Data Assimilation in Dynamic Crop Models Using Particle Swarm Optimization

A novel unsupervised Levy flight particle swarm optimization (ULPSO) method for multispectral remote-sensing image classification

PSOLA: A Heuristic Land-Use Allocation Model Using Patch-Level Operations and Knowledge-Informed Rules

Contact Info

Product

Resources

About