Geomatics, Volume 4, Issue 3 (September 2024) – 7 articles

Climate variability significantly impacts plant growth, making it crucial to monitor ecosystem performance for optimal carbon sequestration, especially in the context of rising atmospheric CO₂ levels. Net Primary Productivity (NPP), which measures the net carbon flux between the atmosphere and plants, serves as a key indicator. This study uses the CASA (Carnegie–Ames–Stanford Approach) model, a radiation use efficiency method, to assess the spatio-temporal dynamics of NPP in Togo from 1987 to 2022 and its climatic drivers. The average annual NPP over 36 years is 4565.31 Kg C ha⁻¹, with notable extremes in 2017 (6312.26 Kg C ha⁻¹) and 1996 (3394.29 Kg C ha⁻¹). Productivity in natural formations increased between 2000 and 2022. While climate change and land use negatively affect Total Production (PT) from 2000 to 2022, they individually enhance NPP variation (58.28% and 188.63%, respectively). NPP shows a strong positive correlation with light use efficiency (r² = 0.75) and a moderate one with actual evapotranspiration (r² = 0.43). Precipitation and potential evapotranspiration have weaker correlations (r² = 0.20; 0.10), and temperature shows almost none (r² = 0.05). These findings contribute to understanding ecosystem performance, supporting Togo’s climate commitments. Full article

Past studies have reported a decreasing planetary albedo and an increasing absorption of solar radiation by Earth since the early 1980s, and especially since 2000. This should have contributed to the observed surface warming. However, the magnitude of such solar contribution is presently unknown, and the question of whether or not an enhanced uptake of shortwave energy by the planet represents positive feedback to an initial warming induced by rising greenhouse-gas concentrations has not conclusively been answered. The IPCC 6th Assessment Report also did not properly assess this issue. Here, we quantify the effect of the observed albedo decrease on Earth’s Global Surface Air Temperature (GSAT) since 2000 using measurements by the Clouds and the Earth’s Radiant Energy System (CERES) project and a novel climate-sensitivity model derived from independent NASA planetary data by employing objective rules of calculus. Our analysis revealed that the observed decrease of planetary albedo along with reported variations of the Total Solar Irradiance (TSI) explain 100% of the global warming trend and 83% of the GSAT interannual variability as documented by six satellite- and ground-based monitoring systems over the past 24 years. Changes in Earth’s cloud albedo emerged as the dominant driver of GSAT, while TSI only played a marginal role. The new climate sensitivity model also helped us analyze the physical nature of the Earth’s Energy Imbalance (EEI) calculated as a difference between absorbed shortwave and outgoing longwave radiation at the top of the atmosphere. Observations and model calculations revealed that EEI results from a quasi-adiabatic attenuation of surface energy fluxes traveling through a field of decreasing air pressure with altitude. In other words, the adiabatic dissipation of thermal kinetic energy in ascending air parcels gives rise to an apparent EEI, which does not represent “heat trapping” by increasing atmospheric greenhouse gases as currently assumed. We provide numerical evidence that the observed EEI has been misinterpreted as a source of energy gain by the Earth system on multidecadal time scales. Full article

In the field of geomatics, artificial intelligence (AI) and especially machine learning (ML) are rapidly transforming the field of geomatics with respect to collecting, managing, and analyzing spatial data. Feature selection as a building block in ML is crucial because it directly impacts the performance and predictive power of a model by selecting the most critical variables and eliminating the redundant and irrelevant ones. Random forests have now been used for decades and allow for building models with high accuracy. However, finding the most expressive features from the dataset by selecting the most important features within random forests is still a challenging question. The often-used internal Gini importances of random forests are based on the amount of training examples that are divided by a feature but fail to acknowledge the magnitude of change in the target variable, leading to suboptimal selections. Shapley values are an established and unified framework for feature attribution, i.e., specifying how much each feature in a trained ML model contributes to the predictions for a given instance. Previous studies highlight the effectiveness of Shapley values for feature selection in real-world applications, while other research emphasizes certain theoretical limitations. This study provides an application-driven discussion of Shapley values for feature selection by first proposing four necessary conditions for a successful feature selection with Shapley values that are extracted from a multitude of critical research in the field. Given these valuable conditions, Shapley value feature selection is nevertheless a model averaging procedure by definition, where unimportant features can alter the final selection. Therefore, we additionally present Conditional Feature Selection (CFS) as a novel algorithm for performing feature selection that mitigates this problem and use it to evaluate the impact of model averaging in several real-world examples, covering the use of ML in geomatics. The results of this study show Shapley values as a good measure for feature selection when compared with Gini feature importances on four real-world examples, improving the RMSE by 5% when averaged over selections of all possible subset sizes. An even better selection can be achieved by CFS, improving on the Gini selection by approximately 7.5% in terms of RMSE. For random forests, Shapley value calculation can be performed in polynomial time, offering an advantage over the exponential runtime of CFS, building a trade-off to the lost accuracy in feature selection due to model averaging. Full article

Land cover maps are frequently produced via the classification of satellite imagery. There is a need for a practicable and automated approach for the generalization of these land cover classification results into scalable, digital maps while minimizing information loss. We demonstrate a method where a land cover raster map produced using the classification of Sentinel 2 imagery was generalized to obtain a simpler, more readable land cover map. A replicable procedure following a formal generalization framework was applied. The result of the initial land cover classification was separated into binary layers representing each land cover class. Each binary layer was simplified via structural generalization. The resulting images were merged to create a new, simplified land cover map. This map was enriched by adding statistical information from the original land cover classification result, describing the internal land cover distribution inside each polygon. This enrichment preserved the original statistical information from the classified image and provided an environment for more complex cartography and analysis. The overall accuracy of the generalized map was compared to the accuracy of the original, classified land cover. The accuracy of the land cover classification in the two products was not significantly different, showing that the accuracy did not deteriorate because of the generalization. Full article

In an era of intense urban development and climate extremes, green infrastructure (GI) has become crucial for creating sustainable, livable, and resilient cities. However, the efficacy of GI is frequently undermined by haphazard implementation and resource misallocation that disregards appropriate spatial scales. This study develops a geographic information system (GIS)-based critical area detection model (CADM) to identify priority areas for the strategic placement of GI, incorporating four main indices—spatial form, green cover, gray cover, and land use change—and utilizing the digital elevation model (DEM), normalized difference vegetation index (NDVI), urban density index (UDI), and up-to-date land use data. By employing the developed method, the study successfully locates priority zones for GI implementation in Saitama City, Japan, effectively pinpointing areas that require immediate attention. This approach not only guarantees efficient resource allocation and maximizes the multifunctional benefits of GI but also highlights the importance of a flexible, all-encompassing GI network to address urbanization and environmental challenges. The findings offer policymakers a powerful tool with which to optimize GI placement, enhancing urban resilience and supporting sustainable development. Full article

Classification of benthic substrates is a core necessity in many scientific fields like biology, ecology, or geology, with applications branching out to a variety of industries, from fisheries to oil and gas. In the first part, a comparative analysis of supervised learning algorithms has been conducted using geomorphometric features to generate benthic substrate maps of the coastal regions of the North Shore of Quebec in order to establish a quantitative assessment of performance to serve as a benchmark. In the second part, a new method using Gaussian mixture models is showcased on the same dataset. Finally, a side-by-side comparison of both methods is featured to provide a qualitative assessment of the new algorithm’s ability to match human intuition. Full article

Optimizing the prediction of maize (Zea mays L.) yields in smallholder farming systems enhances crop management and thus contributes to reducing hunger and achieving one of the Sustainable Development Goals (SDG 2—zero hunger). This research investigated the capability of unmanned aerial vehicle (UAV)-derived data and machine learning algorithms to estimate maize yield and evaluate its spatiotemporal variability through the phenological cycle of the crop in Bronkhorstspruit, South Africa, where UAV data collection took over four dates (pre-flowering, flowering, grain filling, and maturity). The five spectral bands (red, green, blue, near-infrared, and red-edge) of the UAV data, vegetation indices, and grey-level co-occurrence matrix textural features were computed from the bands. Feature selection relied on the correlation between these features and the measured maize yield to estimate maize yield at each growth period. Crop yield prediction was then conducted using our machine learning (ML) regression models, including Random Forest, Gradient Boosting (GradBoost), Categorical Boosting, and Extreme Gradient Boosting. The GradBoost regression showed the best overall model accuracy with R² ranging from 0.05 to 0.67 and root mean square error from 1.93 to 2.9 t/ha. The yield variability across the growing season indicated that overall higher yield values were predicted in the grain-filling and mature growth stages for both maize fields. An analysis of variance using Welch’s test indicated statistically significant differences in maize yields from the pre-flowering to mature growing stages of the crop (p-value < 0.01). These findings show the utility of UAV data and advanced modelling in detecting yield variations across space and time within smallholder farming environments. Assessing the spatiotemporal variability of maize yields in such environments accurately and timely improves decision-making, essential for ensuring sustainable crop production. Full article