Soheil Abadifard

Climate-driven heat and water stress are increasingly compromising rainfed maize yields in transition zones, with significant implications for global food security. While continental-scale models of crop suitability exist, they often fail to capture the high-resolution heterogeneity of agricultural landscapes or distinguish between irrigated and rainfed systems in semi-arid regions. This study models the current and future suitability of rainfed maize in Kansas, USA, using a Maximum Entropy (MaxEnt) approach. To accurately isolate biophysical constraints, we employed a novel data-filtering workflow using the USDA Cropland Data Layer (CDL) and Landsat-based Annual Irrigated Datasets (LANID) to train the model exclusively on rainfed occurrences. We projected suitability shifts for the mid- (2041–2070) and end-of-century (2071–2100) periods under two CMIP6 Shared Socioeconomic Pathways (SSP3-7.0 and SSP5-8.5), using high-resolution CHELSA bioclimatic variables. The model, achieving an Area Under the Curve (AUC) of 0.73 and validated against 30 years of historical USDA production records, reveals a distinct spatial contraction of areas climatically suitable for growing maize. Projections indicate a significant decline in suitability across Western and Central Kansas driven by rising temperatures and precipitation variability, with the most highly suitable optimal habitats projected to decline by approximately 90% by mid-century. These findings quantify mounting climate impacts on maize-growing areas of the Great Plains and provide spatially explicit baselines for the development of regional adaptation strategies and groundwater conservation policies.

Automated Scene Graph Generation (SGG) is challenged by the "Global-Local Dilemma"—the tension between capturing holistic scene context and granular object details. This paper presents a preliminary investigation into a new generative SGG paradigm designed to address this challenge. We introduce a novel, two-track generative framework (GLIIDE) that creates a rich textual intermediary for a Large Language Model (LLM) to extract knowledge. Our hybrid pipeline fuses a YOLO-based track for extracting factual attributes with a DETR-guided track for generating contextual descriptions of object interactions. Our preliminary results on 1,000 images from the Visual Genome dataset demonstrate the potential of this fusion, which achieves a higher Relation Density than relative baselines. This work provides a preliminary proof-of-concept for a generative SGG paradigm that integrates local and global visual information.

The classification of imbalanced data streams, which have unequal class distributions, is a key difficulty in machine learning, especially when dealing with multiple classes. While binary imbalanced data stream classification tasks have received considerable attention, only a few studies have focused on multi-class imbalanced data streams. Effectively managing the dynamic imbalance ratio is a key challenge in this domain. This study introduces a novel, robust, and resilient approach to address these challenges by integrating Locality Sensitive Hashing with Random Hyperplane Projections (LSH-RHP) into the Dynamic Ensemble Diversification (DynED) framework. To the best of our knowledge, we present the first application of LSH-RHP for undersampling in the context of imbalanced non-stationary data streams. The proposed method undersamples the majority classes by utilizing LSH-RHP, provides a balanced training set, and improves the ensemble’s prediction performance. We conduct comprehensive experiments on 23 real-world and ten semi-synthetic datasets and compare LSH-DynED with 15 state-of-the-art methods. The results reveal that LSH-DynED outperforms other approaches in terms of both Kappa and mG-Mean effectiveness measures, demonstrating its capability in dealing with multi-class imbalanced non-stationary data streams. Notably, LSH-DynED performs well in large-scale, high-dimensional datasets with considerable class imbalances and demonstrates adaptation and robustness in real-world circumstances. To motivate our design, we review existing methods for imbalanced data streams, outline key challenges, and offer guidance for future work. For the reproducibility of our results, we have made our implementation available on GitHub.

Ensemble methods are commonly used in classification due to their remarkable performance. Achieving high accuracy in a data stream environment is a challenging task considering disruptive changes in the data distribution, also known as concept drift. A greater diversity of ensemble components is known to enhance prediction accuracy in such settings. Despite the diversity of components within an ensemble, not all contribute as expected to its overall performance. This necessitates a method for selecting components that exhibit high performance and diversity. We present a novel ensemble construction and maintenance approach based on MMR (Maximal Marginal Relevance) that dynamically combines the diversity and prediction accuracy of components during the process of structuring an ensemble. The experimental results on both four real and 11 synthetic datasets demonstrate that the proposed approach (DynED) provides a higher average mean accuracy compared to the five state-of-the-art baselines.