Professor Balthazar

In 2018, I reviewed the landscape of IoT (Internet of Things) technologies for water management in an article published in Irrigation Today magazine, " Using the Power of IoT to Improve Irrigation Water Management " (Osroosh and Adhikari, 2018). Since then, the field has rapidly evolved. This article serves as a focused update, reflecting the current state of IoT in agriculture for 2025. Studies continue to show a potential for water savings exceeding 50% with sensor-based irrigation scheduling . Informed irrigation decisions require real-time data from soil and weather sensor networks at desired resolution and reasonable cost. Wireless sensor networks enable detailed plant monitoring across diverse field areas. The need for wireless sensors and actuators has fueled the growth of IoT solutions, particularly Low-Power Wide-Area Networking (LPWAN). LPWAN technologies connect low-cost, low-power sensors to cloud-based services. In 2025, a range of wireless and IoT connectivity...

  Following my previous discussion on the limitations of synthetic data in agricultural AI (" Stop Swinging That Hammer: Why Synthetic Data is Banging Up Agricultural AI "), a pertinent question arose: Why do researchers opt for synthetic data over real-world data in the first place? It's a question that warrants careful consideration, particularly given the implications for the validity and applicability of AI in agriculture.     One would expect a data-driven approach – the design and execution of field experiments to generate targeted datasets – to be the prevailing methodology. However, this is not consistently observed. Several factors appear to contribute to the preference for synthetic data: Perceived Complexity of Real Data:  There exists a perception that the acquisition and preprocessing of real-world agricultural data is excessively challenging. While it is true that real data can be complex and require significant effort, this should not deter rigorous sc...

  Ever feel like AgriTech companies are selling you a magic potion? You hand over your greenhouse data – VPD, PAR, the whole shebang – and they promise incredible insights, all thanks to their secret AI sauce. It's like a chef's special recipe – delicious, but don't dare ask what's in it! Just drink it up and trust the magic, right? Well… maybe not.       The Promise of Prediction The promise is seductive: instant wisdom, turbo-charged growth, and the ability to predict which tomato will end up in the ketchup bottle before it even ripens. (Okay, maybe not that specific, but you get the idea.) But what if there's more to the story than just AI wizardry? What if we have a whole toolbox of methods at our disposal, and we're only using one, slightly mysterious, tool? Let's explore! So, what's the real deal with all these "smart" solutions? At their core, many AgriTech solutions aim to do one thing: predict . They want to forecast what's going ...

  This article builds upon my previous work on canopy temperature measurements and the Crop Water Stress Index (CWSI), and I highly recommend reading " Decoding VPD and CWSI for Optimized Crop Water Management " before continuing. My research has focused on two key challenges in the conventional CWSI approach: the calculation of CWSI itself, and how it's applied to irrigation scheduling (the CWSI algorithm). I've developed improvements in both areas, specifically by using a transpiration-based CWSI calculation and a dynamic threshold algorithm. These enhancements are detailed below.   CWSI Definitions Traditional CWSI Definition  As discussed previously, CWSI is traditionally defined as: CWSI = (ΔTm - ΔTl) / (ΔTu - ΔTl) where ΔTm is the measured canopy-to-air temperature difference, ΔTl is the temperature difference under non-limiting soil water availability (well-watered plant canopy), and ΔTu is the temperature difference for a non-transpiring canopy (dead plant)....

Remember when we talked about how important calibration is for your thermal sensors when calculating CWSI? (" Decoding VPD and CWSI for Optimized Crop Water Management "). Well, today we're going to explore how to get accurate readings without  shelling out for a pricey blackbody calibrator.   Blackbody calibrators are the usual go-to for checking and adjusting your IRT or thermal camera.   Blackbody calibrators are the usual go-to for checking and adjusting your IRT or thermal camera . They provide a stable, known temperature source. But they can be expensive.  And speaking of expensive, high-quality infrared thermometers (IRTs) in the $800-$1000+ range often include a significant cost for factory calibration—sometimes as much as half the total price. This is a labor-intensive process. However, the raw materials used to make IRTs are relatively inexpensive, and the components are often very similar regardless of where the IRT is sold (U.S. vs. other countries). So...

  As an AgriTech advocate, I might surprise you by suggesting you could reduce your reliance on technology, particularly sensors, in certain aspects of farming.  While I firmly believe in the power of reliable sensors for research and many applications, I'm also seeing a shift in the agricultural landscape, driven by AI and other factors, that makes me reconsider their universal recommendation for growers.  I'll delve into the broader concerns about technology costs and corporate influence in future posts, but for today, let's focus on this question: Can you effectively manage crops based on plant cues 𝘸𝘪𝘵𝘩𝘰𝘶𝘵 a sensor? The answer is yes, in some cases. Many plant-based water stress detection methods, including those using sophisticated sensors like infrared thermal cameras , dendrometers, or sap flow meters, ultimately rely on similar principles.  If a method works for you, by all means, continue using it. But if you're exploring options, I particularly recom...

  The question of whether plant-based crop monitoring methods, like the crop water stress index (CWSI), can replace soil moisture sensors is frequently debated. The short answer is: No. Why monitor plant water status using a plant-based method? Common reasons include detecting water stress for irrigation scheduling, perceived shortcomings of soil moisture sensors, or simply following established research. Whatever your reason, it's important to understand the limitations. Plant-based methods, including those relying on canopy surface temperature (used in CWSI calculations) or dendrometers (and similar tools), are insufficient on their own. Both biotic and abiotic stresses influence plant water status. Biotic stresses originate from living organisms (e.g., pests, pathogens, weeds), while abiotic stresses are caused by non-living environmental factors (e.g., extreme temperatures, drought, salinity, nutrient deficiencies). This means a simple canopy feedback, like temperature or trunk...

  My stance on AI in agriculture isn't a simple "for" or "against." Four years ago, when I first raised concerns about AI's potential downsides for agricultural innovation (related post: " How Artificial Intelligence Is Convoluting Agricultural Engineering "), many agreed. Today, it seems everyone's immersed in AI, and critical voices are harder to find. This shift is concerning. The perception of AI in agriculture has changed dramatically. What was once a focus on machine learning and deep learning has broadened, with everything now labeled simply as "AI." The emergence of generative AI, particularly large language models (LLMs), has further complicated things, leaving many behind. While some are still focused on traditional machine learning or the intricacies of Bayes' theorem, a quiet revolution is underway. This shift, driven by generative AI, is both exhilarating and terrifying, reminiscent of the impact of dynamite.   The re...

Agricultural AI holds immense promise for transforming farming. We envision AI-powered tractors, drones, and robots that can revolutionize efficiency and ease on the farm. But the reality is that we aren't seeing these transformative changes as quickly or effectively as we'd hoped. One key reason is the way we're approaching data, specifically the increasing reliance on synthetic data. Synthetic data is artificially created information that mimics real-world data. In agricultural AI, this often means generating images of plants, fields, and other agricultural elements. Synthetic data seems like a good solution at first. It's hard to get enough real data from farms. For example, it's difficult to collect many pictures of rare plant diseases or to capture all the different conditions in the fields. So, people try to create this data artificially. This seems easier and faster than collecting real data. Also, some people believe that having more data, even if it's s...

Remember that time you spent months fine-tuning a machine learning model to predict crop yields? You meticulously collected data, tweaked parameters, and finally achieved what seemed like a breakthrough. But then, a sudden shift in weather patterns threw everything off, and your predictions went haywire. Sound familiar? You're not alone. Many agricultural researchers are hitting a wall with traditional machine learning, and it's time to talk about why. The truth is, while these traditional approaches have their place, they're often no match for the disruptive power of  generative AI . Generative AI refers to a class of artificial intelligence models designed not just to analyze data, but to  create  new content. This can range from text and images to code and even complex predictive models. And at the heart of this revolution are  Large Language Models (LLMs) . These powerful models are trained on massive amounts of text data, allowing them to understand and generate...