Prerpints.org logo
Preprint
Review

Decision Support Systems in Silvicultural Practices and the Essential Prioritization of Ecosystem Services: A Review

Altmetrics

Downloads

144

Views

61

Comments

0

A peer-reviewed article of this preprint also exists.

This version is not peer-reviewed

Submitted:

16 December 2023

Posted:

18 December 2023

You are already at the latest version

Alerts
Abstract
In this study, tree selection/plantation DSS (Decision Support Systems) were reviewed and assessed based on essential objectives in the available literature. We reviewed existing DSS using multiple data sources and available online resources such as web interfaces. We compared the existing DSS, focusing primarily on five primary objectives in this study, which DSS may address when it comes to the tree selection, including a) Climate resilience, b) Infrastructure/Space Optimization, c) Agroforestry, d) Ecosystem services, e) Urban sustainability. Climate resilience of tree species and urban sustainability is addressed relatively less in existing systems, which can be holistically internalized in future DSS tools Based on this review, DNN (Deep Neural Networks) is recommended to address achieving trade-offs between complex objectives such as maximizing ecosystem services, climate resilience of tree species, maintaining Agroforestry, and other benefits.
Keywords: 
Subject: Environmental and Earth Sciences  -   Sustainable Science and Technology

1. Introduction

The global climate is changing and is predicted to change even faster in the near future (IPCC 2022). The importance of planting trees for climate change adaptation and mitigation is increasing as forests act as carbon sinks (Nunes et al. 2020, Yang 2023). This is particularly true in areas with desertification and complex environmental problems that require sound processes that allow the ever-growing human population to benefit from the ecosystem services of the environment (Poch et al., 2002, Prince and Safriel 2021). Also, in many cases, ecosystem services are not easily quantified monetarily, taken for granted, and often involve moral and ethical principles (Kiker et al. 2009). The rapid growth of tree planting and land use conversion from grassland to forests directly impact ecosystem services, including increased regulation and provision of services (Vihervaara et al. 2012). However, further planning is needed to ensure that local environmental issues and cultural values are internalized, enabling additional ecosystem services such as wood availability, water quality, biodiversity enrichment, and carbon sequestration (Muller and Turner 2007).
However, this type of land use change does not always increase ecosystem services, as grassland biomes are often viewed as having potential for forest restoration and planting, which typically reduces biodiversity and ecosystem services once these grasslands/savannahs are converted, leading to significant conservation measures for forest and grassland biomes, plantation strategies as well as separate ecosystem services need to be identified (Veldman et al. 2015). Furthermore, identifying the suitable tree species for tree adaptability is crucial for future climate scenarios, especially in urban areas, as changing climates lead to the loss of tree species, which can lead to a reduction in ecosystem services such as Urban Heat Island (UHI) mitigation, which can pose a challenge for adaptation and mitigation strategies to human-caused climate change (Lanza and Stone Jr. 2016).
Using deep neural networks (DNNs), a decision support system (DSS) can be trained to learn from a large dataset of tree data, including information about tree species, climate, soil conditions, and other factors influencing tree growth and survival. This is because using neural networks was proposed three decades ago to solve forest management problems by integrating forest knowledge with artificial intelligence (AI; Kourtz 1990). AI greatly benefits sustainability and preserving ecosystem values, as increasing disruptions in a changing world can only be managed beyond human intelligence (Silvestro et al. 2022). Furthermore, despite the various DSS and AI used, the appointment of appropriate project managers is crucial to the execution and subsequent success of a project (Muller and Turner 2007).
Our study reviews various DSSs and compares them based on their objectives and applications. Furthermore, we provide a literature review focusing on the need for ecosystem service-focused DSS and discuss the potential applications of DNN for these systems.

2. Review of existing DSS tools for tree selection and plantations

One of the earliest DSSs for tree plantations in forestry was developed at the University of Canterbury, a framework-based system coded in Prolog. The focus was on knowledge-based decision support by linking to the Forest management information system (FMIS) database or Geographic Information Systems (GIS), enabling location-based access to information about the field microenvironment such as soils, climate, elevation, and previous land/crop use and current conditions along with multiple management options for optimization (Mason 1996). This section reviews existing DSS on tree selection and plantations using apparent keywords like ‘DSS’, ‘Decision Support tool’, ‘Tree selection,’ etc., as Google Scholar search (Figure 1).
We focus on five primary objectives in this study, which DSS may address when it comes to the tree selection, including a) Climate resilience, b) Infrastructure/Space Optimization, c) Agroforestry, d) Ecosystem services, and e) Urban sustainability (Figure 2).
Further efforts to develop a DSS for tree plantations began in the 2000s using GIS with a focus on street and neighborhood tree plantations while also attempting to address management aspects such as DSS-based strategies for reducing energy, fuel, and pesticide/fertilizers for plantation management (Randall et al. 2003). In addition, the focus was also expanded to include aspects such as soil property-based tree planting, the feasibility of the planting region, tree age, species diversity, shade, and canopy coverage (Kirnbauer et al. 2009). It is also essential to conduct an existing urban tree cover (UTC) analysis before tree planting decisions, using object-oriented satellite image analysis to identify existing vegetation cover and land use types (McGee III et al. 2012).
Mitigating a region’s hydrological problem also requires selecting suitable species, prioritizing sites for revegetation, and simulating other hydro-climatological conditions annually. These aspects were included in China’s bilingual GUI decision support re-vegetation program’s tool ReVegIH, which also could reduce sediment load release through afforestation modeling (McVicar et al. 2007).
Multi-lingual programming (C++ and Fortran) based DSS, known as Motti Simulator, developed by the Natural Resources Institute Finland (Luke), was also used for tree selection based on detailed forest stand dynamics and incorporating the tree growth and yield models (Saksa et al. 2021). Additionally, simplified open-source and open-code DSS such as PT2 (Prairie and Tree Planting Tool) allowed users to explore and delineate areas of interest for planting or managing trees/prairie using scaled dimensional drawing tools and then selecting seeds/woody plants for the respective soils with a dropdown menu. This also enabled the selection and calculation of financial costs and long-term management options (Tyndall 2021).
Nevertheless, advances in machine learning in recent years have enabled the selection of tree species incorporating climate variability using MaxEnt to determine the suitability and resilience of trees in different climate scenarios. A current example is the online platform “Which Plant Where” in Australia, which was developed using Python, Django and PostgreSQL (Tabassum et al., 2023). In addition, others use tree selection tools developed by the United States Department of Agriculture (USDA) such as the Tree Advisor and the Woody Plant Selection Tool for Multi-functional Purposes, using MySQL and the Drupal framework (Bentrup and Dosskey 2022). Also, Spatio-temporal Urban Tree DSS was developed using ensemble CAD and GIS tools, which integrates detailed 3D trees into urban design, which allows testing of tree placement, species selection, solar shade exposure, etc., with valuable elements of computational botany and light engineering technology makes this possible (White and Langenheim 2019).
Although tree planting decision support systems have addressed tree selection ecosystem services such as UHI mitigation, only simple filtering techniques with limited variables that filter the attributes from the tree database have been used (Werbin et al. 2020). In addition, ensemble models that use higher resolution datasets are also proposed to infer the potential suitability and realized distribution of tree species through batch generalization. This is a boosting method where Random Forests (RF), Gradient-booster trees (GBT), and Generalized linear models (GLM) are used, which are used by the meta-learner, i.e., linear regression, can be further processed (Bonannella et al. 2022).
We compare various DSS for tree selection/plantation based on their objectives, programming language framework and software (Table 1) along with their comparison with the primary objectives (Figure 2). Table 1 summarizes DSS in urban tree plantation, agroforestry, etc. revealing a prevalent trend towards utilizing R and Python tools. However, the technologies employed span a broad spectrum, encompassing languages such as C#, C++, .NET, Python, R, and Java, and web development tools like HTML, CSS, and JavaScript. The emphasis on these languages also suggests a shared recognition within the community of their effectiveness in handling data-driven tasks and facilitating interdisciplinary collaboration in environmental decision-making.
This comparison is crucial as it emphasizes the core concept of tree plantation as the DSS for tree selection/plantation operates on a foundational structure encompassing Species, Location, and Value. The data sources include research articles from Google Scholar, DSS web interfaces, and grey literature, as the hands-on use of DSS web interfaces was essential to identify the capabilities and objectives of various DSS. During the review process, textual comparison reveals significant patterns and themes in the literature. The DSS outputs encompass recommendations with critical objectives and advocate advanced techniques like Deep Neural Networks (DNN) to enhance decision-making precision in tree selection and plantation, thereby offering more informed and insightful guidance.
Moreover, the Venn diagram of DSS comparison reflects how existing DSS have combinations of objectives such as Infrastructure/Space Optimization with urban sustainability. Climate resilience and urban sustainability of trees are addressed least, whereas Infrastructure/Space Optimization and ecosystem services are addressed relatively more in DSS- tools. Nevertheless, the existing DSS addresses all issues at different times as evident from the analysis (Table 2).
Table 2. The DSS reviewed and the relevant objectives they address.
Table 2. The DSS reviewed and the relevant objectives they address.
# DSS Climate resilience Infrastructure/Space Optimization Agroforestry Ecosystem Services Urban sustainability
1 Knowledge-based DSS No No Yes No No
2 Prototype decision support system No Yes No No Yes
3 ReVegIH decision support tool Yes No Yes No No
4 Prototype decision support system (Randall) No Yes No No Yes
5 Decision Support Tool - Precision Forestry No Yes Yes No No
6 Virginia UTC assessment process No Yes No Yes Yes
7 Right Place, Right Tree—Boston No No No Yes Yes
8 Which Plant Where? Yes Yes No No Yes
9 Tree Advisor USDA No No Yes Yes No
10 Plant-Best Yes Yes No Yes No
11 Spatio-Temporal Decision Support System for Street trees No Yes No No Yes
12 Florida Agroforestry Decision Support System (FADSS) Yes Yes Yes Yes No
13 PT2 (Prairie and Tree Planting Tool) No Yes Yes Yes No
14 Diversity for Restoration (D4R) Yes No Yes Yes No
15 Citree Yes Yes No Yes Yes
16 i-tree Yes No Yes Yes Yes
17 Unique decision-support tool for Cocoa and Coffee No No Yes Yes No

4. The need for an Ecosystem Services-focused DSS

It is crucial to understand the ecosystem services received from trees during selection and planting, as trees provide various regulatory (carbon sequestration, air pollution reduction) and provisioning (timber, tree crops) services where the non-market values sometimes exceed commercial values and threats such as wildfires and pests must be considered for resilience (Cavender-Bares et al. 2022). Also, models such as the Natural Capital Protocol can be applied to improve agroforestry decision-making and evaluation at the farm level. They describe the connection between a natural capital asset, its condition, the resulting ecosystem services, and the benefits the people derive from those services. Better representation of benefits can also promote the public benefits of agroforestry at the farm level (Marais et al. 2019).
Satellite datasets and IDF (Intensity, Duration and Frequency)-based flood models can provide valuable information about the flooding and waterlogging situation in regions where monsoon and persistent floods occur. The areas affected by flooding and erosion can be identified based on flood depth and flow velocity forecasts for 25-, 50- and 100-year return periods (Quirogaa et al. 2016). Therefore, the selection of tree species adapted to this waterlogging must be assessed based on literature evaluating parameters such as stomatal conductance and net photosynthesis since some tree species show a reduction in these two processes after flooding (Anderson and Pezeshki 2001). In addition, trees such as poplars in riparian zones are very tolerant of flooding because nitrogen metabolism is not affected by flooding compared to species such as Oak and Beech, which are sensitive to successive flooding, and the depth and duration of flooding also need to be taken into account in detailed findings (Kreuzwieser et al. 2002).
It is essential to understand the dynamics of the UHI effect. There are regional and zonal differences, including in urban areas, as although trees are effective in reducing air temperature in areas with high building density, they are ineffective in built-up areas with low building density, and therefore, high-density trees with taller trunks are recommended for built-up areas (Aboelata and Sodoudi 2020). Changes in land use and land cover can influence local surface temperatures. For example, as previously irrigated croplands and forests transform into built-up urban areas over time, this can increase air and land surface temperatures. Conversely, a transition from bare land cover to urban areas could decrease average land surface temperature (LST) for semi-arid regions (Yosef et al. 2022, Sahdev et al. 2023). This highlights the significant influence of both vegetation and urban development on LSTs at the local scale. Vegetation has a cooling effect through transpiration, shading, and rainwater retention.
Similarly, urbanized zones contribute to temperature reduction than regions such as exposed soil or rocky terrains due to their surface properties and materials that promote convection more effectively (Rasul et al. 2017). There is a unique approach to UHI mitigation that consists of creating a regional Heat Vulnerability Index (HVI) that includes socioeconomic (family income, age, building density) and environmental data (e.g., LST, vegetation) to inform decision-making (Johnson et al. 2012), which helps increase urban canopy cover with the most suitable tree species. To mitigate UHI, urban areas need to be categorized as high- and low-density, as land use and availability of trees in cities are limited.
Furthermore, Nature-based solutions (NbS) to air pollution can be implemented zone-wise by involving the plantations. Air pollution-tolerant species such as Shorea robusta, Ficus religiosa, and Mangifera indica have high tolerance to pollutants and high metal accumulation capacity in industrial areas. Dust removal and deposition are excellent in residential areas in Azadirachta indica, Dalbergia sissoo, and Ficus religiosa (Menon and Sharma 2021). Slope protection and landslide mitigation tools include Plant-Best, developed in the R statistical programming language (Gonzalez-Ollauri and Mickovski 2017).
Many factors influence tree plantations, including the value and placement of trees, particularly in urban areas. This includes public lands, parks and roadsides, and private lands, i.e., residential properties (Kowarik 2023). Kirkpatrick et al. (2012) suggested that small fruit trees are more aesthetic and practical on private lands. About agroforestry, a study found that the management of forests involves significant uncertainty regarding future timber prices, tree growth, and the impact of climate-related changes on tree growth. Since most forest owners prefer to avoid risk and tree growth and timber prices are unpredictable, the study suggests the following implications: longer rotations should be compared to the recommended guidelines. There should be a greater preference for mixed stands than deterministic calculations suggest; the concentration of timber revenues should be less focused on the final harvest, as currently recommended. The consistent retention of multiple timber assortments in the stand is beneficial, indicating the pursuit of more uneven stand structures (Pukkala and Kellomäki 2012).
Therefore, the suitability process must include mixed stands, not just monoculture recommendations. However, this may not be the case for all tree species as agarwood monoculture plantations could also be favorable regarding growth as it is endangered (Nath et al. 2022). Nevertheless, plantation agriculture in tropical countries must be managed based on polyculture systems and not monocultures since the ecosystem services provided by the former are much higher as they include improving biodiversity, pollination, and biological pest control even in the context of small-scale silviculture (Yahya et al. 2017). Hirsch et al. (2023) found species-specific tolerance to drought and traffic pollution in urban areas, suggesting using certain tree species along roads and in residential areas.
DSS, such as the FADSS (Florida Agroforestry DSS), addressed economic and environmental services and utilized GIS databases that included vital datasets such as tree attributes, infrastructure, climate, soil, and cropping, including critical levels such as crucial agroforestry management practices (Ellis et al. 2000). It is also essential to include soil datasets such as soil pH, sand content etc., for tree species Species Distribution Models (SDM) as soil variables are strong predictors of habitat suitability (Henderson et al. 2023). The soil datasets are often neglected in many SDMs, so these datasets should be some of the core variables in the decision support system. Finally, recent developments in tree selection DSS include the Diveristy for Restoration (D4R) tool, which allows users to make multi-selections from the menu for restoration objectives, ecosystem services, seeding zones, climate, and other environmental data in decision-making for individual and combined tree species selection (Fremout et al., 2021).

5. Proposed use of DNN in DSS for Tree selection/plantations

In order to improve decision-making in Urban Forestry for sustainable and livable cities, AI has been increasingly used in recent years (Schepers 2023). However, only half of the studies involving the use of AI manage to take into account aspects such as limitations of these methods, including robustness and lack of precision in the absence of some datasets, combined use of discrete and continuous data variables, overfitting, collinearity, etc., (Araújo et al. 2021). The application of AI in forestry can be improved by incorporating XAI (Explainable Artificial Intelligence), LTNL (Learning To Not Learn), and FUL (Feature Unlearning) methods that provide a qualitative and quantitative comparison of model accuracy and add explanations through the use of predefined annotation matrices, i.e., expert knowledge that can improve these deep learning models. Therefore, combining XAI, FUL and expert knowledge can improve the understanding of how the model works instead of simple model results (Cheng et al. 2022).
Furthermore, the use of CNN (Convolutional Neural Networks) is increasing significantly with a large number of applications in agriculture/agroforestry DSS generally based on frameworks such as Keras, Tensorflow, Tensorflow-Keras, PyTorch, Tensorflow-PyTorch and Deeplearning 4j (Altalak et al. 2022). In addition, the applications of DNN for intelligent geographic data analysis in DSS in agriculture have shown promising results, mainly when BPNN (Back-Propagation Neural Network) based prediction models are used to predict agricultural indicator values (Zeng et al. 2022, Araujo et al. 2023). In addition, DNN-based species distribution models, show better results than traditional models, including DNN created using bootstraps to improve the prediction performance of species distribution. These can be built in the Python environment using the Scikit-learn package with bootstrapping aggregation (bagging) performed in the R statistics package boot to train the DNN (Rew et al. 2021). Regardless, CNN-based SDMs offer broader advantages, including better learning of non-linear environmental descriptors, compelling distribution predictions of environmental descriptors, and the use of high-dimensional data, enabling improved collection of information about environmental landscapes structured on tensors rather than local values of environmental factors (Deneu et al. 2021). Similarly, the ecosystem service component of a tree plantation DSS can be better understood and improved through these tensors (Unawong et al. 2022), i.e., various functions of multiple vectors, because ecosystem services include multiple services and complex relationships such as the existing environment or land-use can be considered in one vector. The ecosystem services can be considered as multi-linear functions of the vector (Zhang et al. 2023).
TensorFlow uses the term "Tensor" to denote the primary data structure used in deep learning algorithms. This "Tensor" represents a multi-dimensional array of numerical values (Singh and Manure 2019). In addition, deep neural networks have been widely used in recent years. This rise in the popularity of deep learning models can be attributed to TensorFlow, an open-source deep learning framework, because this framework provides users with the opportunity to access pre-defined network-trained deep learning classification (and regression) models while allowing customizable training of their personalized or custom datasets (Pally and Samadi 2022).
The TensorFlow Deep Neural Network (TF-DNN) is used in the Python environment as the primary model of this study because TF-DNN has been applied in GIS studies, which have shown higher spatial prediction accuracy than other techniques such as Random Forests (RF), Support Vector Machine (SVM) and Logistic Regression (LR) (Truong et al. 2023). The TF-DNN can be applied with semi-supervised learning with multivariate multilayer perceptron with training datasets, where the soil, climate, and landscape-environmental layers can be used to determine the land suitability of the plant species in the study, with the results providing continuous better-decision potential when validating through K-fold cross-validation (Bhullar et al. 2023).
For the proper implementation of the TF-DNN, it is essential to use multiple libraries, including TensorFlow, Keras, NumPy, and Matplotlib, where Keras is used as a backend to build and implement the TF-DNN algorithm as TensorFlow acts as a numerical computing library. The Numpy library is helpful for many mathematical functions that operate on arrays, and Matplotlib is similarly used for visualizing statistical outputs (Osah et al. 2021).
Therefore, the utilization of DNN is essential for improving the precision and efficacy of DSS, contributing to sustainable and well-informed tree selection and plantation strategies in both urban and regional environments.

6. Conclusions

Based on this review, it is essential to consider the focus on increasing climate-resilient tree selection in DSS along with requirements of urban sustainability to maximize ecosystem services in urban environments. Incorporating DNN can also enhance decision-making when multiple ecosystem services and agroforestry benefits are considered, especially when the goal is better predictive modeling capabilities in the context of tree plantations.
Moreover, the primary objectives outlined in the review need to be addressed and incorporated simultaneously, which needs to be included in the reviewed DSS. Applying DNN in future DSS tools will enable the internalization of these challenging objectives, particularly when finding a balance between complex trade-offs such as maximizing ecosystem services, climate resilience of tree species, and maintaining agroforestry benefits.

Author Contributions

For research articles with several authors, a short paragraph specifying their individual contributions must be provided. The following statements should be used “Conceptualization, S.R., R.Y., and Y.Y.; methodology, Y.Y.; software, S.R.; validation, R.Y., Y.Y.; formal analysis, S.R.; data curation, S.R.; writing—original draft preparation, S.R., R.Y.; writing—review and editing, S.R., R.Y.; visualization, S.R.; supervision, Y.Y.; funding acquisition, Y.Y. All authors have read and agreed to the published version of the manuscript.” Please turn to the CRediT taxonomy for the term explanation. Authorship must be limited to those who have contributed substantially to the work reported.

Funding

This research received no external funding.

Data Availability Statement

This is a review of historical and existing platforms and no new data were created.

Conflicts of Interest

The authors declare no conflict of interest.

Abbreviations

AI Artificial Intelligence; BPNN Back-Propagation Neural Network; CNN Convolutional Neural Networks; DNN Deep Neural Networks; DSS Decision Support System; D4R Diversity for Restoration; FADSS Florida Agroforestry Decision Support System; FMIS Forest Management Information System; FUL Feature Unlearning; GBT Gradient Booster Trees; GIS Geographic Information Systems; GLM Generalized Linear Models; HVI Heat Vulnerability Index; IDF Intensity, Duration and Frequency; IPCC International Panel for Climate Change; LST Land Surface Temperature; LTNL Learning To Not Learn; NbS Nature-based Solutions; RF Random Forests; SDM Species Distribution Modelling; SVM Support Vector Machine; TF-DNN TensorFlow Deep Neural Network; UHI Urban Heat Island; USDA United States Department of Agriculture; UTC Urban Tree Cover; XAI Explainable Artificial Intelligence.

References

  1. IPCC. 2022. Climate Change 2022: Impacts, adaptation, and vulnerability. Cambridge (UK) and New York (Ny, US): Cambridge University Press. 3056. Available at: https://www.ipcc.ch/report/sixth-assessmentreport-3working-group-ii/.
  2. Nunes L., J. , Meireles, C. I., Pinto Gomes, C. J., & Almeida Ribeiro, N. M. Forest contribution to climate change mitigation: Management oriented to carbon capture and storage. Climate 2020, 8, 21. [Google Scholar] [CrossRef]
  3. Yang H, Ciais P, Frappart F, Li X, Brandt M, Fensholt R, Fan L, Saatchi S, Besnard S, Deng Z, Bowring S, Wigneron J-P. Global increase in biomass carbon stoc dominated by growth of northern young forests over past decade. Nature Geoscience 2023, 16, 886–892. [CrossRef]
  4. Poch M, Comas, J., Rodriguez-Roda, I, Sanchez-Marri, M, Cortes, U. 2002. Ten years of experience in Designing and Building real Environmental Decision Support Systems. What have we learnt?. International Congress on Environmental Modelling and Software. 168. https://scholarsarchive.byu.edu/iemssconference/2002/all/168.
  5. Prince S, Safriel U. Land use and degradation in a desert margin: the Northern Negev. Remote Sensing 2021, 13, 2884. [CrossRef]
  6. Kiker GA, Bridges TS, Varghese A, Seager TP, Linkov I. Application of multi criteria decision analysis in environmental decision making. Integrated Environmental Assessment and Managementb 2009, 1, 95–108. [CrossRef]
  7. Vihervaara, P. , Marjokorpi, A, Kumpula, T., Walls, M., & Kamppinen, M. Ecosystem services of fast-growing tree plantations: A case study on integrating social valuations with land-use changes in Uruguay. Forest Policy and Economics 2012, 14, 58–68. [Google Scholar] [CrossRef]
  8. Muller R, Turner R. The influence of project managers on project success by type of project. European Management Journal 2007, 25, 298–309. [CrossRef]
  9. Veldman J., W. , Overbeck, G. E., Negreiros, D., Mahy, G., Le Stradic, S., Fernandes, G. W., Durigan, G., Buisson, E., Putz, F.E., & Bond, W. J. Where tree planting and forest expansion are bad for biodiversity and ecosystem services. BioScience 2015, 65, 1011–1018. [Google Scholar] [CrossRef]
  10. Lanza, K. , & Stone Jr, B. Climate adaptation in cities: What trees are suitable for urban heat management? Landscape and Urban Planning 2016, 153, 74–82. [Google Scholar] [CrossRef]
  11. Kourtz, P. Artificial intelligence: a new tool for forest management. Canadian Journal of Forest Research 1990, 20, 428–437. [Google Scholar] [CrossRef]
  12. Silvestro, D. , Goria, S. , Sterner, T., & Antonelli, A. Improving biodiversity protection through artificial intelligence. Nature sustainability 2022, 5, 415–424. [Google Scholar] [CrossRef]
  13. Mason E., G. Planning forest establishment operations with a computerised decision-support system: a case study analysis of decision-making over a full rotation. NZJ For. Sci 1996, 26, 222–234. [Google Scholar]
  14. Randall T., A. , Churchill, C. J., & Baetz, B. W. A GIS-based decision support system for neighbourhood greening. Environment and Planning B: Planning and Design 2003, 30, 541–563. [Google Scholar] [CrossRef]
  15. Kirnbauer, M. C. , Kenney, W. A., Churchill, C. J., & Baetz, B. W. A prototype decision support system for sustainable urban tree planting programs. Urban forestry & urban greening 2009, 8, 3–19. [Google Scholar] [CrossRef]
  16. McGee III, J. A. , Day, S. D., Wynne, R. H., & White, M. B. Using geospatial tools to assess the urban tree canopy: Decision support for local governments. Journal of Forestry 2012, 110, 275–286. [Google Scholar] [CrossRef]
  17. McVicar, T. R. , Li, L., Van Niel, T. G., Zhang, L., Li, R., Yang, Q., Zhang, X. P., Mu, X. M., Wen, Z. M., Liu, W.Z., Zhao, Y.A., Liu, Z.H., & Gao, P. Developing a decision support tool for China's re-vegetation program: Simulating regional impacts of afforestation on average annual streamflow in the Loess Plateau. Forest Ecology and Management 2007, 251, 65–81. [Google Scholar] [CrossRef]
  18. Saksa, T. , Uusitalo, J., Lindeman, H., Häyrynen, E., Kulju, S., & Huuskonen, S. Decision support tool for tree species selection in forest regeneration based on harvester data. Forests 2021, 12, 1329. [Google Scholar] [CrossRef]
  19. Tyndall, J. Prairie and tree planting tool—PT 2 (1.0): a conservation decision support tool for Iowa, USA. Agroforestry Systems 2021, 1-16.
  20. Tabassum, S. , Beaumont, L. J., Shabani, F., Staas, L., Griffiths, G., Ossola, A., & Leishman, M. R. Which Plant Where: A Plant Selection Tool for Changing Urban Climates. Arboriculture & Urban Forestry (AUF) 2023, 49, 190–210. [Google Scholar]
  21. Bentrup, G. , & Dosskey, M. G.. Tree Advisor: A Novel Woody Plant Selection Tool to Support Multifunctional Objectives. Land 2022, 11, 397. [Google Scholar] [CrossRef]
  22. White, M. R. , & Langenheim, N. (2019). A spatio-temporal decision support system for designing with street trees. In Geospatial Intelligence: Concepts, Methodologies, Tools, and Applications (pp. 533-560). IGI Global.
  23. Werbin, Z. R. , Heidari, L., Buckley, S., Brochu, P., Butler, L. J., Connolly, C., Bloemendaal, L.H., McCabe, T.D., Miller, T.K., & Hutyra, L.R.. A tree-planting decision support tool for urban heat mitigation. PloS one 2020, 15, e0224959. [Google Scholar] [CrossRef]
  24. Bonannella, C. , Hengl, T, Heisig, J., Parente, L., Wright, M. N., Herold, M., & De Bruin, S. Forest tree species distribution for Europe 2000–2020: mapping potential and realized distributions using spatiotemporal machine learning. PeerJ 2022, 10, e13728. [Google Scholar]
  25. Gonzalez-Ollauri, A. , & Mickovski, S.B. Plant-Best: A novel plant selection tool for slope protection. Ecological Engineering 2017, 106, 154–173. [Google Scholar] [CrossRef]
  26. Ellis, E. A. , Nair, P. K. R., Linehan, P. E., Beck, H. W., & Blanche, C. A. A GIS-based database management application for agroforestry planning and tree selection. Computers and electronics in agriculture 2000, 27(1-3), 41-55. [CrossRef]
  27. Fremout, T. , Thomas, E, Taedoumg, H., Briers, S., Gutiérrez-Miranda, C. E., Alcázar-Caicedo, C., Lindau, A., Kpoumie, H.M., Vincenti, B., Kettle, C., Ekue, M., Atkinson, R., Jalonen, R., Gaisberger, H., Elliott, S, Brechbuhler, E., Ceccarelli V, Krishnan, S., Vacik, H., Wiederkehr-Guerra, G., Salgado-Negret, B., Gonzalez, M.A., Ramirez, W., Moscoso-Higuita, L.G., Vasquez, A., Cerron, V., Maycock, C., & Muys, B. Diversity for Restoration (D4R): Guiding the selection of tree species and seed sources for climate-resilient restoration of tropical forest landscapes. Journal of Applied Ecology 2022, 59, 664–679. [Google Scholar] [CrossRef]
  28. Vogt, J. , Gillner, S, Hofmann, M., Tharang, A., Dettmann, S., Gerstenberg, T., Schmidt, C., Gebauer, H., Van de Riet, K., Berger, U., & Roloff, A. Citree: A database supporting tree selection for urban areas in temperate climate. Landscape and Urban Planning 2017, 157, 14–25. [Google Scholar] [CrossRef]
  29. Nowak, D. J. , Maco, S, & Binkley, M. J. A. C. i-Tree: Global tools to assess tree benefits and risks to improve forest management. Arboricultural Consultant 2018, 51, 10–13. [Google Scholar]
  30. Van der Wolf, J. , Jassogne, L., Gram, G. I. L., & Vaast, P. Turning local knowledge on agroforestry into an online decision-support tool for tree selection in smallholder’s farms. Experimental Agriculture 2019, 55, 50–66. [Google Scholar] [CrossRef]
  31. Cavender-Bares, J. M. , Nelson, E, Meireles, J. E., Lasky, J. R., Miteva, D. A., Nowak, D. J., Pearse, W.D., Helmus, M.R., Zanne, M.E., Fagan, W.F., Mihiar, C., Muller, N.Z., Kraft, N.J.B., & Polasky, S. The hidden value of trees: quantifying the ecosystem services of tree lineages and their major threats across the contiguous US. PLOS Sustainability and Transformation 2022, 1, e0000010. [Google Scholar] [CrossRef]
  32. Marais, Z. E. , Baker, T.P., O’Grady, A. P., England, J. R., Tinch, D., & Hunt, M. A. A natural capital approach to agroforestry decision-making at the farm scale. Forests 2019, 10, 980. [Google Scholar] [CrossRef]
  33. Quirogaa, V. M. , Kurea, S, Udoa, K., & Manoa, A. Application of 2D numerical simulation for the analysis of the February 2014 Bolivian Amazonia flood: Application of the new HEC-RAS version 5. Ribagua 2016, 3, 25–33. [Google Scholar] [CrossRef]
  34. Anderson, P. H. , & Pezeshki, S.R. Effects of flood pre-conditioning on responses of three bottomland tree species to soil waterlogging. Journal of Plant Physiology 2001, 158, 227–233. [Google Scholar] [CrossRef]
  35. Kreuzwieser, J. , Fürniss, S, & Rennenberg, H. Impact of waterlogging on the N-metabolism of flood tolerant and non-tolerant tree species. Plant, Cell & Environment 2002, 25, 1039–1049. [Google Scholar] [CrossRef]
  36. Aboelata, A. , & Sodoudi, S. Evaluating the effect of trees on UHI mitigation and reduction of energy usage in different built up areas in Cairo. Building and Environment 2020, 168, 106490. [Google Scholar] [CrossRef]
  37. Yosef, R., S. Rakholia, A. Mehta, A. Bhatt, S. Kumbhojkar. Land Surface temperature regulation ecosystem service: a case study of Jaipur, India, and the urban island of Jhalana Forest Reserve. Forests 2022, 13, 1821. [Google Scholar] [CrossRef]
  38. Sahdev, S., R. Yosef, S. Rakholia, A. Mehta, N. Yadav. 2023, Accepted 10 Dec 2023. Bidecadal Analysis of Ecosystem Services and Urbanization Effects in the Western Himalayas: A Case Study from Haldwani, Uttarakhand. Remote Sensing Applications: Society and Environment.
  39. Rasul, A. , Balzter, H, & Smith, C. Applying a normalized ratio scale technique to assess influences of urban expansion on land surface temperature of the semi-arid city of Erbil. International journal of remote sensing 2017, 38, 3960–3980. [Google Scholar] [CrossRef]
  40. Johnson, D. P. , Stanforth, A, Lulla, V., & Luber, G. Developing an applied extreme heat vulnerability index utilizing socioeconomic and environmental data. Applied Geography 2012, 35, 23–31. [Google Scholar] [CrossRef]
  41. Menon, J. S. , & Sharma, R. Nature-based solutions for co-mitigation of air pollution and urban heat in Indian cities . Frontiers in Sustainable Cities 2021, 3, 705185. [Google Scholar] [CrossRef]
  42. Kowarik, I. The Mediterranean tree Acer manspessulanum invades urban green spaces in Berlin. Dendrobiology 2023, 89, 20–26. [Google Scholar] [CrossRef]
  43. Kirkpatrick, J. B. , Davison, A, & Daniels, G. D. Resident attitudes towards trees influence the planting and removal of different types of trees in eastern Australian cities. Landscape and urban planning 2012, 107, 147–158. [Google Scholar] [CrossRef]
  44. Pukkala, T. , & Kellomäki, S. Anticipatory vs adaptive optimization of stand management when tree growth and timber prices are stochastic. Forestry: An International Journal of Forest Research 2012, 85, 463–472. [Google Scholar] [CrossRef]
  45. Nath, P. C., Nath, A. J., Sileshi, G. W., & Das, A. K. (2022). Growth and Coppicing Ability of the Critically Endangered Agarwood (Aquilaria Malaccensis Lam.) Tree in Monoculture and Polyculture in North East India. Journal of Sustainable Forestry, 1-13. [CrossRef]
  46. Yahya, M. S. , Syafiq, M., Ashton-Butt, A., Ghazali, A., Asmah, S., & Azhar, B. Switching from monoculture to polyculture farming benefits birds in oil palm production landscapes: Evidence from mist netting data. Ecology and evolution 2017, 7, 6314–6325. [Google Scholar]
  47. Hirsch M, Boddeker H, Albrecht A, Saha S. Drought tolerance differs between urban tree species but is not affected by the intensity of traffic pollution. Trees 2023, 37, 111–131. [CrossRef]
  48. Henderson, A. F. , Santoro, J.A., & Kremer, P. Impacts of spatial scale and resolution on species distribution models of American chestnut (Castanea dentata) in Pennsylvania, USA. Forest Ecology and Management 2023, 529, 120741. [Google Scholar] [CrossRef]
  49. Schepers, T. 2023. Automated decision-making systems and the epistemic condition of moral responsibility - Public sector decision-making with decision aids. Master Thesis, University of Twente, The Netherlands. 76 pp.
  50. de Lima Araújo, H. C. , Martins, F. S., Cortese, T. T. P., & Locosselli, G. M. Artificial intelligence in urban forestry—A systematic review. Urban Forestry & Urban Greening 2021, 66, 127410. [Google Scholar] [CrossRef]
  51. Cheng, X. , Doosthosseini, A, & Kunkel, J. Improve the deep learning models in forestry based on explanations and expertise. Frontiers in Plant Science 2022, 13, 902105. [Google Scholar] [CrossRef]
  52. Altalak, M. , Ammad uddin, M, Alajmi, A., & Rizg, A. Smart agriculture applications using deep learning technologies: A survey. Applied Sciences 2022, 12, 5919. [Google Scholar] [CrossRef]
  53. Zeng, C. , Zhang, F, & Luo, M. A deep neural network-based decision support system for intelligent geospatial data analysis in intelligent agriculture system. Soft Computing 2022, 26, 10813–10826. [Google Scholar] [CrossRef]
  54. Araujo SO, Peres RS, Filipe L, Manta-Costa A, Lidon F, Ramalho JC, Barata J. 2023. Intelligent data-driven decision support for agricultural systems-ID3SAS. IEEE Access. [CrossRef]
  55. Rew, J. , Cho, Y, & Hwang, E. A robust prediction model for species distribution using bagging ensembles with deep neural networks. Remote Sensing 2021, 13, 1495. [Google Scholar] [CrossRef]
  56. Deneu, B. , Servajean, M, Bonnet, P., Botella, C., Munoz, F., & Joly, A. Convolutional neural networks improve species distribution modelling by capturing the spatial structure of the environment. PLoS computational biology 2021, 17, e1008856. [Google Scholar] [CrossRef]
  57. Unawong W, Yaemphum S, Nathalang A, Chen Y, Domec J-C, Tor-ngern P. Variations in leaf water status and drought tolerance of dominant tree species growing in multi-aged tropical forests in Thailand. Scientific Reports 2022, 12, 6882. [CrossRef]
  58. Zhang, P. , Ren, H, Dong, X., Wang, X., Liu, M., Zhang, Y., Zhang, Y., Huang, J., Dong, S., & Xiao, R. Understanding and Applications of Tensors in Ecosystem Services: A Case Study of the Manas River Basin. Land 2023, 12, 454. [Google Scholar] [CrossRef]
  59. Singh, P. , & Manure, A. (2019). Learn TensorFlow 2.0: Implement Machine Learning and Deep Learning Models with Python. Apress.
  60. Pally, R. J. , & Samadi, S. Application of image processing and convolutional neural networks for flood image classification and semantic segmentation. Environmental Modelling & Software 2022, 148, 105285. [Google Scholar] [CrossRef]
  61. Truong, T. X. , Nhu, V. H., Phuong, D. T. N., Nghi, L. T., Hung, N. N., Hoa, P. V., & Bui, D. T. A New Approach Based on TensorFlow Deep Neural Networks with ADAM Optimizer and GIS for Spatial Prediction of Forest Fire Danger in Tropical Areas. Remote Sensing 2023, 15, 3458. [Google Scholar] [CrossRef]
  62. Bhullar, A. , Nadeem, K., & Ali, R. A. Simultaneous multi-crop land suitability prediction from remote sensing data using semi-supervised learning. Scientific Reports 2023, 13, 6823. [Google Scholar] [CrossRef]
  63. Osah, S. , Acheampong, A. A., Fosu, C., & Dadzie, I. Deep learning model for predicting daily IGS zenith tropospheric delays in West Africa using TensorFlow and Keras. Advances in Space Research 2021, 68, 1243–1262. [Google Scholar] [CrossRef]
Preprints 93536 g001
Figure 1. Flow diagram of the purpose of this study emphasizing the key concept and objectives of DSS.
Figure 1. Flow diagram of the purpose of this study emphasizing the key concept and objectives of DSS.
Preprints 93536 g001
Preprints 93536 g002
Figure 2. The figure represents Venn diagram of DSS (number represent the number of DSS fitting in the categories) and their major objectives to draw similarities and differences in DSS objectives. Details relevant to this figure are provided in Table 2.
Figure 2. The figure represents Venn diagram of DSS (number represent the number of DSS fitting in the categories) and their major objectives to draw similarities and differences in DSS objectives. Details relevant to this figure are provided in Table 2.
Preprints 93536 g002
Table 1. Comparison of various DSS developed for tree selection/plantation.
Table 1. Comparison of various DSS developed for tree selection/plantation.
DSS Name (Provisional) Software/language/framework Objective Type Reference
1 Knowledge-based DSS Prolog Forest plantations DSS Mason 1996
2 Prototype decision support system SMODT; ArcTrees; Treemodules | Visual Basic Analysis (VBA) Urban tree plantation suitability Kirnbauer et al. 2009
3 ReVegIH decision support tool C#, Visual Basic, C++, .NET Tree species selection with Ecohydrological modelling McVicar et al. 2007
4 Prototype decision support system (Randall) ArcView GIS Extension | Avenue Neighbourhood greening Randall et al. 2003
5 Decision Support Tool - Precision Forestry HprAnalys, ArcGIS, Motti stand simulator Tree species selection with stand dynamics Saksa et al. 2021
6 Virginia UTC assessment process ERDAS; ISODATA Object-orientedclassification Urban Tree Canopy analysis McGee III et al. 2012
7 Right Place, Right Tree—Boston R packages - shinydashboard;leaflet;tigris;DT Tree plantation DSS for UHI mitigation Werbin et al. 2020
8 Which Plant Where? Python; Django; PostgreSQL Plant Selection Tool for climate resilience and sustainability Tabassum et al. 2023
9 Tree Advisor USDA MySQL; Drupal Woody Plant Selection Tool for Multifunctional objectives Bentrup and Dosskey 2022
10 Plant-Best R Plant Selection Tool for slope protection Gonzalez-Ollauri and Mickovski 2017
11 Spatio-Temporal Decision Support System for Street trees QGIS/ArcGIS; exlevel GrowFX; Autodesk; AutoCAD; ForestPro Detailed 3D trees for Urban Design White and Langenheim 2018
12 Florida Agroforestry Decision Support System (FADSS) Delphi; SQL Agroforestry planning and tree selection Ellis et al. 2000
13 PT2 (Prairie and Tree Planting Tool) HTML; CSS; Javascript Prairie and Tree Planting selection and financial cost estimation Tyndall 2021
14 Diversity for Restoration (D4R) JavaScript, Python, and R. Ecosystem Restoration and Agroforestry Fremout et al. 2021
15 Citree PHP; MariaDB server Tree selection for urban areas in temperate climate Vogt et al. 2017
16 i-tree USDA Java; Javascript; Python Multi-module suite for Urban Tree structures and ecosystem service evaluation Nowak et al. 2018
17 Unique DSS for agroforestry systems R; HTML Decision-support tool for coffee and cocoa agroforestry systems Van der Wolf et al. 2019
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
Copyright: This open access article is published under a Creative Commons CC BY 4.0 license, which permit the free download, distribution, and reuse, provided that the author and preprint are cited in any reuse.
Prerpints.org logo

Preprints.org is a free preprint server supported by MDPI in Basel, Switzerland.

facebook logotwitter logolinkedin logo
MDPI Initiatives
Important Links
Subscribe

Disclaimer

Terms of Use

Privacy Policy

© 2024 MDPI (Basel, Switzerland) unless otherwise stated